Skip to content

About

A curated list of tools, guides, playbooks, and resources for the NVIDIA DGX Spark (GB10 Grace Blackwell personal AI supercomputer).

Topics

awesomeawesome-listblackwelldgx-sparkgb10llmnvidia

Resources

Readme
CC0-1.0 license

Contributing

Contributing
Activity

Stars

76 stars

Watchers

0 watching

Forks

7 forks
Report repository
BranchesTags

Latest commit

 

History

84 Commits

Folders and files

NameName
Last commit message
Last commit date
.githooks
.githooks
 
 
.github
.github
 
 
.gitignore
.gitignore
 
 
LICENSE
LICENSE
 
 
README.md
README.md
 
 
contributing.md
contributing.md
 
 

Repository files navigation

Awesome DGX Spark Awesome

A curated list of awesome tools, guides, playbooks, and resources for the NVIDIA DGX Spark, the GB10 Grace Blackwell personal AI supercomputer.

DGX Spark is a desktop machine built on the GB10 Grace Blackwell Superchip (SM 12.1 / sm_121), with 128 GB of unified CPU+GPU memory. You can link two units over 200 Gb/s networking to run larger models. This list collects community projects for setting it up, serving models, fine-tuning, benchmarking, and day-to-day operation.

Platform essentials: aarch64 · CUDA 13.x · sm_121 · 128 GB unified memory · 200 Gb/s ConnectX-7

Contents

Official

  • NVIDIA/dgx-spark-playbooks - Step-by-step DGX Spark playbooks spanning vLLM, SGLang, llama.cpp, NVFP4 quantization, speculative decoding, cuTile kernels, NCCL, and two- and three-node clustering.

Setup & Configuration

  • a1exus/sparky - Self-hosted DGX Spark LLM stack, vLLM, Ollama, and a llama.cpp router serving every cached GGUF behind Traefik, with mDNS, Cloudflare Tunnel, and Tailscale ingress.
  • Albatross1382/onnxruntime-aarch64-cuda-blackwell - ONNX Runtime 1.24.4 CUDA shared libraries for sm_121 on aarch64, loaded through the Rust ort crate or dlopen.
  • botAGI/AGmind - One-command private RAG stack for DGX Spark, Dify with vLLM, Weaviate, RAGFlow, and Docling across 30+ containers, plus two-node clustering over 200 Gb/s QSFP.
  • christopherowen/dgx-spark-memory-saver - Patch for nvidia-uvm that packs GPU page tables on 64 KiB DGX Spark kernels, 3.03 GiB recovered versus stock 64 KiB and about 1.8 GiB per node over 4 KiB.
  • Chrizz-lab/GB10-Agentig-Coding-Framework - Agentic coding stack for DGX Spark with dual-vLLM Qwen3 and CrewAI orchestration.
  • csabakecskemeti/dgx-spark-community-playbooks - Community playbook collection for DGX Spark, covering dual-Spark RDMA inference, heterogeneous RoCE clustering, and local Claude Code.
  • Entrpi/dgx-spark-serving-mode - Three-state serving-mode script for DGX Spark that pares GNOME and maintenance timers down to multi-user.target for 10-15 GB more unified memory.
  • Fulton-Engineering-Services/dgx-spark-wheels - Wheel index for GB10 covering packages with no upstream aarch64 build: flash-attn, sageattention, flashinfer, and torch 2.13 on CUDA 13.3, each kernel-launch verified.
  • getainode/ainode - Browser-UI AI appliance for GB10 doing inference and LoRA fine-tuning, with UDP-discovered multi-node clustering, TP=2 on the current 0.5.x and TP=4 only on 0.4.x.
  • GuigsEvt/dgx_spark_config - Source-build guide for LLVM, Triton, and PyTorch 2.9.1 against sm_121, with release wheels and ~1.5x on 8192 FP16 GEMM versus the stock cu130 build.
  • HeKun-NVIDIA/dgx-spark-openclaw - Two-script deploy of a local LLM plus OpenClaw frontend, Qwen3.5-35B-A3B and MiniMax-M2.5-REAP-NVFP4 on a GB10 NVFP4-kernel vLLM image, or GLM-4.7-Flash on Ollama.
  • HendrikSchoettle/ragflow-dgx-spark - Build and deploy pipeline for RAGFlow v0.24.0 on DGX Spark aarch64, with a source-built onnxruntime-gpu wheel for sm_121 and multilingual OCR.
  • install-safe-press/gb10-playbooks - Chinese-language walkthrough of NVIDIA's official GB10 playbooks covering the basics and AI-agent sections, with hardware, DAC cabling, and Dell switch-config notes of its own.
  • JetBrains-Hardware/spark-setup - Remote deploy scripts for Qwen, GPT-OSS 120B, Nemotron 3 NVFP4, and Gemma 4 on vLLM, with MTP speculative decoding holding 14.4 tok/s at 200k context.
  • jschmied/dgx-spark-setup-guide - End-to-end DGX Spark guide: llama-server router mode, key-only SSH, DCGM monitoring, SWE-bench evals, and vLLM appendices where MTP-3 takes Qwen3.6-35B-A3B NVFP4 from 73 to 102 tok/s single-stream.
  • m9h/neurocontainers-arm - Prebuilt causal-conv1d wheel plus four published neuroimaging containers built against NGC PyTorch CUDA 13, with locally built FreeSurfer 8.2.0 packages inside two of them.
  • mARTin-B78/dgx-spark_lite-llm_llama-swap_vllm_llama-cpp_ollama - Multi-engine LLM stack for DGX Spark with llama-swap idle eviction behind a LiteLLM gateway, plus a harness pairing llama-benchy with a 69-scenario tool-calling bench.
  • natolambert/dgx-spark-setup - Training setup for CUDA 13.x on aarch64, cu130 vLLM wheels, SDPA over flash-attn, swap-off OOM guards, and profiled SFT, DPO, and LoRA batch ceilings.
  • seitzbg/onnxruntime-gpu-sm121-aarch64 - Prebuilt onnxruntime-gpu 1.27.1 aarch64 wheel, CUDA 13.x execution provider for sm_121, 7.3x over CPU on GB10.
  • Sggin1/DGX-SPARK - Dated GB10 lab notes, TurboQuant 3-bit KV cache at 240K context, dual-Spark 195 Gb/s RDMA, and sm_121a FP4 SASS evidence.
  • sjug/dgx-spark-ethernet-patch - Binary patch for the DGX Spark OOBE ethernet-detection bug, an 8-byte aarch64 HasInternet edit for FastOS 1.120.38.
  • Th0rgal/cuda-blackwell-carry-bug - Repro for a PTXAS bug that drops the carry flag between separate inline-asm blocks on GB10 sm_121, with a Docker harness and a 128-bit reference path to compare against.
  • timothystewart6/ubuntu-gb10 - Ubuntu 24.04 setup for GB10 in place of DGX OS, Ansible roles for NVIDIA driver, CUDA 13.x, DOCA-OFED, dual-node NCCL, and a 33-check read-only verify playbook.
  • tonyd2wild/DGX-Spark-Hard-Poweroff-Fix - Diagnosis of GB10 log-less hard power-offs as an embedded-controller cut, fixed by a 2200 MHz clock cap and page-cache drops at 5% decode cost.

Inference & Serving

vLLM

  • 0xSero/deepseek-v4-flash-0731-spark-sparkinfer - DeepSeek-V4-Flash-0731 on one DGX Spark via EXL3 and SparkInfer sparse MLA, 38.1 tok/s median c1 code decode at a 262K limit, 432-byte NVFP4 KV disabled.
  • AEON-7/vllm-ultimate-dgx-spark - DGX Spark vLLM 0.29.0 image compiled for sm_121a with DSpark quantized Markov heads, DFlash 2 at 3.39x single-stream on Qwen3.8-27B, and Triton NVFP4 KV cache.
  • airawatraj/dgx-spark-nemotron-super-agent - Nemotron-3-Super-120B agentic stack on DGX Spark scoring 93 of 100 on tool-eval-bench, with spark-arena 23.7 tok/s.
  • albond/DenseSpark-Qwen3.8-27B - Qwen3.8-27B INT4 AutoRound on one DGX Spark with vLLM 0.27.1 and sm_121 kernels, MTP drafting, 49.1 tok/s at one request and 260.2 at 16.
  • albond/SingleSpark-Qwen3.8-Flash-Next - Qwen3.8-Flash-Next on one DGX Spark from a 101 GiB four-bit checkpoint with the n-gram table kept resident, 43.34 tok/s median single stream at 65,536 context.
  • Anemll/dspark-vllm-gx10 - Two-node GB10 port of DeepSeek-V4-Flash DSpark to vLLM 0.25.1 with nvfp4_ds_mla KV format and a b12x MXFP4 MoE backend, 48.5 tok/s decode at TP=2.
  • atcuality2021/vllm-gb10-gemma4 - Vendored ManthanQuant 3-bit Lloyd-Max KV-cache compression patched into vLLM's attention backends for Gemma 4 on GB10, 5.12x smaller KV at ~0.978 cosine, quantized in NumPy on the Grace CPU.
  • Avarok-Cybersecurity/dgx-vllm - vLLM image for DGX Spark, tag v22 from February 2026, NVFP4 through a software E2M1 conversion and Marlin backends, ~42 tok/s on Qwen3-Next-80B-A3B-Instruct-NVFP4, 20% over AWQ INT4.
  • bjk110/spark_vllm_docker - vLLM serving from one DGX Spark at TP=1 to two over 200 Gb/s RoCE at TP=2, 42 presets, pinned DeepSeek-V4-Flash-0731 and Solar-Open2-250B production images with rollbacks.
  • blazux/qwen3.8-Flash-DGX - Qwen3.8-Flash-Next NVFP4 on one GB10 with the 48 GiB PLE table mmapped from NVMe, fixing a prefix-cache hit that restored an all-zero Mamba state and a non-deterministic sparse-attention top-k.
  • dolf3131/qwen3.8-flash-next-dgx-spark - NVIDIA's Qwen3.8-Flash-Next NVFP4 on one DGX Spark, 47.7 GiB n-gram table paged to SSD swap, 33.0 tok/s single-stream at 524K context, plus the PLE-offload hang at TP=1.
  • EmilHaase/DGX-Spark-VLLM-Hydra-Manager - vLLM manager for DGX Spark with sm_121a source builds and UMA KV-cache limits for multi-model launch.
  • Entrpi/ds4-spark-vllm - One-command 2-bit DeepSeek-V4-Flash vLLM install on a single DGX Spark, 85 GiB IQ2_XXS plus Q2_K checkpoint validated against antirez/ds4 at 1.75 tok/s under enforce-eager.
  • eugr/spark-vllm-docker - vLLM Docker for one to eight DGX Sparks, native PyTorch distributed by default with Ray opt-in, and 42 run-recipe.sh YAML recipes, Qwen3.8-Flash-Next-NVFP4 solo to GLM-5.2-NVFP4 on eight nodes.
  • gitcommit90/glm-5.3-one-spark - GLM-5.3-Flash EXL3 2.05 bpw on one DGX Spark under vLLM TP1 with DFlash2 K5, 40.1 tok/s on code and 29.9 on prose at 262K context.
  • jordanovski/overdrive - Web console and CLI for launching concurrent vLLM containers on DGX Spark, with preflight GPU-memory admission control and a SWE-bench page comparing resolution rates.
  • mark-ramsey-ri/vllm-dgx-spark - Run vLLM on 1-to-N DGX Spark servers (single Spark, 2 via direct cable, or 3+ via switched fabric) to serve or benchmark LLMs.
  • MiaAI-Lab/Nemotron-Labs-3-Puzzle-75B-DGX-Spark - Nemotron-Labs-3-Puzzle-75B-A9B NVFP4 hybrid Mamba MoE on one DGX Spark, vLLM 0.24 launcher with aarch64 NCCL and FlashInfer cuda_ipc patches, 256K context, MTP k=3.
  • MiaAI-Lab/Ornith-1.5-35B-A3B-DGX-Spark - Ornith-1.5-35B-A3B NVFP4 with in-checkpoint MTP on one DGX Spark, 86.3 to 440 tok/s at 24 streams, plus two b12x patches for CUDA-graph capture.
  • MiaAI-Lab/Qwen3.8-Flash-Next-Single-DGX-Spark - Qwen3.8-Flash-Next NVFP4 on one DGX Spark under vLLM with the PLE table packed and memory-mapped, 48.7 tok/s prose single stream and 162.9 at eight on 512k YaRN.
  • mouwp2026/qwen3.8-flash-next-gx10-mtp-hashk - Qwen3.8-Flash-Next on one GB10 with the PLE table compressed to a 12.8 GB HashK build, FP8 dense cast, and a shrunk-vocabulary MTP head, 104 tok/s at six streams.
  • mrexodia/Kolibri-1-vLLM-DGX-Spark - Kolibri-1 FP8 on one DGX Spark under vLLM 0.29 with Aleph Alpha's inference plugin, 262,144-token context, 42.0 tok/s generation and 97% prefix-cache hits in a pi coding-agent run.
  • omnia-projetcs/spark-dgx - Interactive vLLM Docker launcher for DGX Spark, 22 preset model configs from single-node NVFP4 to TP=4 Ray clusters, 10 with measured TTFT and concurrency tables.
  • Sapid-Labs/vllm-spark-arena - Crowd-optimization arena for vLLM on sm_121, scoring sitecustomize.py patches over a pinned wheel as paired ratios, gated on byte-identical output and a held-out timed speedup.
  • sayyidfareed/qwen3.8-flash-next-dgx-spark-1m - Qwen3.8-Flash-Next NVFP4 at a validated 989,801-token request on one ASUS GX10, clean PLE pages released by MADV_DONTNEED watermark, 5/5 needles at 26.7 tok/s single stream.
  • spark-arena/sparkrun - One-command launcher for vLLM, SGLang, and llama.cpp on one or more DGX Sparks, where --tp 2 means two hosts over auto-detected RDMA, plus git-based recipe registries.
  • sudoingX/dgx-spark-ling - Official Ling-3.0-flash INT4 on one DGX Spark under vLLM with its MTP layer, 38.7 tok/s against 35.2 for the community GGUF, but 7.9 against 33.6 at 45K context.
  • timothystewart6/vllm-gb10 - Prebuilt GHCR vLLM image for GB10 (sm_121a) with NCCL and FlashInfer built from source, pinned by SHA, digest or version, and latest promoted only after a four-model verification gate.
  • tonyd2wild/Qwen3.8-Flash-Next-NVFP4-DGX-Spark - NVIDIA's own Qwen3.8-Flash-Next NVFP4 checkpoint byte for byte on one DGX Spark, the 47.68 GiB PLE table left on NVMe and gathered 16 rows per token, 43.9 tok/s median.

llama.cpp

  • 0xBakeer/qwen38-flash-next-spark - Qwen3.8-Flash-Next on one DGX Spark with the 51B lookup table on SSD, in two profiles that differ by 2x: 88 tok/s rewriting a file against 32 on prose.
  • cahlen/glm-5.3-flash-GGUF-1bit-dgx-spark - GLM-5.3-Flash as a 1-bit UD-IQ1_S GGUF on one DGX Spark for agentic coding, where leaving --reasoning-budget unset returns nothing on 35% of turns against 0 of 80 with it.
  • croll83/llama.cpp-dgx - Deprecated llama.cpp fork for DGX Spark, kept for its TurboQuant TQ3_0 KV cache and weight kernels, which upstream does not expose.
  • gitcommit90/angelslim-hy3-iq1m-mtp-dgx-spark - AngelSlim Hy3 IQ1_M GGUF with MTP drafting on one DGX Spark through patched llama.cpp, 100K context, 18-19 tok/s on prose and 26-30 on code and JSON.
  • marknx/flash-next-gguf-tools - Qwen3.8-Flash-Next GGUF split across one DGX Spark and an RTX 5090 over 10 GbE, 140 tok/s aggregate at eight streams that OOM-kill the single box, plus converter fixes.
  • phuongncn/qwen3.6-27b-speedhack-gx10-dgx-spark - DFlash block-diffusion spec-decode llama.cpp fork for Qwen3.6-27B on GB10, 7-11 to 38-40 tok/s coding via a p_min drafting threshold, and 60-66 to 113 on a 35B-A3B MoE.
  • Sapid-Labs/llamacpp-spark-arena - Crowd-optimization arena for llama.cpp CUDA kernels on sm_121, with a thermal gate, alternating baseline and candidate runs, and referee-verified held-out speedup.
  • shamily/gemma4-llama-dgx-spark - Dockerized llama.cpp for all four Gemma 4 models on GB10, benchmarked at 69.9 tok/s tg128 for the 26B-A4B MoE against 11.0 for the dense 31B.
  • sxuff/ternary-bonsai-2-27b-gx10 - Ternary-Bonsai-2-27B on one DGX Spark under the PrismML llama.cpp fork, PTQ1_0 (1.75 bpw) at 34.21 tok/s tg128 in 5.53 GiB, build pinned to commit 1a07bfa.
  • Weschera/GLM-5.3-Flash-Unsloth-1x-DGX-Spark - GLM-5.3-Flash UD-IQ3_XXS GGUF on one DGX Spark under Unsloth's llama.cpp fork, MTP n=2 at 20.8 tok/s against 15.5 without, 64K context.

SGLang

  • 0xBakeer/ling3-flash-spark - Ling-3.0-flash MXFP4 on one DGX Spark pairing the Humming MoE backend and an online FP8 LM head with DSpark drafting, with the cookbook and notebook configs selectable for comparison.
  • 0xWhiteMage/qwen3.8-27b-kearuga-sglang-dgx-spark-dflash2 - Qwen3.8-27B Kearuga target with a distilled DFlash 2 drafter on SGLang for one DGX Spark, 35.33 tok/s at C1 and 108.90 at C4, +14.5% and +10.8% over stock.
  • BTankut/dgx-spark-sglang-moe-configs - Tuned Triton MoE configs for GB10's 101,376-byte shared memory limit, where SGLang defaults need 147,456 and EAGLE crashes, GLM-4.7-FP8 at 20-27 tok/s on four nodes.
  • hasso5703/dgx-spark-qwen38 - One-command SGLang service on GB10 for seven switchable Qwen3.8 targets, Qwen3.8-27B NVFP4 at 71.4 tok/s greedy single-stream median via DFlash2 and Qwen3.8-Flash-Next 176B at 262K context.
  • InquiringMinds-AI/longcat-next-multimodal - LongCat-Next 75B-A3B any-to-any multimodal through one SGLang process on a single GB10, image generation and voice-clone TTS on OpenAI endpoints at w8a8_int8 after 4-bit collapsed both.
  • mark-ramsey-ri/sglang-dgx-spark - Run SGLang on 1-to-N DGX Spark servers (single Spark, 2 via direct cable, or 3+ via switched fabric) to serve or benchmark LLMs.
  • MiaAI-Lab/Nemotron3.5-Lightning-DGX-Spark-RTX-5090-6000-PRO - Nemotron 3.5 Lightning 30B-A3B NVFP4 with its DSpark draft model on one DGX Spark via SGLang, 4.93M-token KV pool, 48 max concurrent, up to 1M per request.
  • MiaAI-Lab/Qwen3.8-27B-SGLang-DGX-Spark - Qwen3.8-27B NVFP4 on one DGX Spark with EAGLE/MTP, DSpark and DFlash2 as measured swap-in modes, GDN in bf16 and the scheduler pinned to the X5 cores.
  • pangoleen/qwen3.8-27b-dgx-spark-dflash2 - Qwen3.8-27B NVFP4 on one DGX Spark with a DFlash2 draft budget of 16, 64-78 tok/s single stream on code against ~30 on chat, 387 aggregate at 32 streams.
  • robbiemu/dgx-spark-inference - SGLang services on one DGX Spark under systemd with per-role memory budgets, refusing a launch that will not fit, on a digest-pinned v0.5.14-cu130 runtime.
  • scottgl9/sglang-spark-gb10-optimizations - SGLang fork that routes NVFP4 through Marlin FP4 where CUTLASS returns zeros on sm_121, Qwen3.5-122B-A10B at 43-45 tok/s with ~90% MTP acceptance.
  • ubehera/sglang-spark - SGLang patch stack for DGX Spark with an sm_121a-only sgl-kernel 0.4.4 wheel, model-agnostic TP=2 launch recipes at NEXTN k=3, and a systemd watcher that stops wedged nodes.
  • Weschera/Qwen3.8-27B-NVFP4-DFlash2-DGX-Spark - Qwen3.8-27B NVFP4 with DFlash2 on one DGX Spark, digest-pinned, where a boot-time fp8_gemm autotune race decides between 42 and 33 tok/s for the process lifetime.

Other Engines

  • 0xBakeer/deepseek-v41-flash-spark - DeepSeek-V4.1-Flash on one DGX Spark in a plain-PyTorch engine with routing-ranked expert keep-sets, 24.3-36.6 tok/s by workload at 44% keep, above the reliable 39% default.
  • 0xBakeer/TandemLLM - Inference engine for Qwen3.8-27B on one DGX Spark with StairCut draft-tree sizing and custom NVFP4 kernels, 49.89 tok/s single request with the lookup store off against 13.69 plain greedy.
  • antirez/ds4 - DwarfStar C inference engine for DeepSeek, GLM and Qwen3.8 Flash Next with a make cuda-spark target, DeepSeek V4 Flash Q2 prefill above 820 t/s through 65K, decode 18.1 to 13.8.
  • ashhart/TensorFold - Speculative-decoding LLM server for Apple Silicon and NVIDIA with replies equal to serial decoding, CUDA engines for one or two DGX Spark, GLM-5.3-Flash at 256k tokens on two.
  • Avarok-Cybersecurity/atlas - Pure Rust and CUDA inference engine in one 75 MB binary with GB10 as verified target, ahead of vLLM 0.27.1 at every C=1 to C=128 rung on Qwen3.8-27B NVFP4.
  • Baekpica/ds4-dfm-rs - Rust-host continuation of ds4 with DGX Spark as release reference and recorded gates per model artifact, Qwen3.8 Flash Next Q5 at 1,323 prefill and 28.93 decode tok/s with MTP 2.
  • blake-snc/sm121-kernels - Hand-written PTX kernel library for sm_121 in 259 files, covering flash attention, GEMM, Gated DeltaNet, and MoE, driver-only via cudarc with FP8 attention at ~108 TFLOPS.
  • calico88x/DGX-Model-Manager - Control plane for managing Ollama, SGLang, vLLM, llama.cpp, LocalAI, and ComfyUI on DGX Spark, with roles, API tokens, and Hugging Face cache inventory.
  • HawkBearPig/dgpp - C++/CUDA inference engine for one, two, or four DGX Spark with tensor parallelism over RoCE, 29 benchmarked configurations across GLM, Qwen, DeepSeek, and MiMo models.
  • jdaln/dgx-spark-inference-stack - Docker serving stack for a single DGX Spark with on-demand model loading, automatic idle shutdown, and a unified API gateway.
  • joshhu/meetaclawtaipei - Three concurrent NVFP4 vLLM models on one DGX Spark with a 3-LLM voice-clone roommate demo.
  • kshetrajna12/sparkstation - Headless control plane for DGX Spark model fleets with profile-driven placement over vLLM and SGLang, unified-memory admission control, and LiteLLM gateway sync.
  • lrozewicz/vLLM-Moet-GB10 - vLLM-Moet fork for one GB10 running GLM-5.3-Flash at ~29 tok/s on code and DeepSeek-V4-Flash-0731 at ~21, via 2-bit expert planes plus an FP4 delta tier.
  • mark-ramsey-ri/trt-dgx-spark - TensorRT-LLM serving for 1 to N DGX Spark with the aarch64 nvcr 1.2.1 container and TP set by node count, verified on 1 and 2 nodes.
  • MiaAI-Lab/exllamav3 - ExLlamaV3 fork that builds on aarch64 GB10, with NVFP4 and FP8 paged-attention KV at about 3.5x the context per GB of fp16, plus DFlash2, DSpark, and MTP drafting.
  • MiaAI-Lab/Qwen3.8-Flash-Next-Single-DGX-Spark-TensorFold - Qwen3.8-Flash-Next top-5-expert INT4-AutoRound checkpoint on one DGX Spark under TensorFold's Zig engine, 64.4 tok/s prose at c1 and 200.9 at c8, about 10% lower capability.
  • r0b0tlab/glm53-flash-exl3-exllamav3-gb10 - ExLlamaV3 and TabbyAPI runtime for GLM-5.3-Flash EXL3 2.25 bpw with DFlash2 on one GB10, a fail-closed memory guard, and 259,993-token retrieval at 262,144 context.
  • rdaum/eider - Rust and CUDA inference server for sm_121 NVFP4 with no tensor runtime, Qwen3.8-Flash-Next with its 51B PLE table paged from NVMe at ~300 tok/s uncached prefill, ~13 MTP decode.
  • rdoiron/mimo-mods-for-dgx-spark - Ten vLLM runtime patches for MiMo-V2.5 on sm_121a, with a CUTLASS block-FP8 bypass and a backported tool-call corruption fix (PR #42969).
  • sf-stav/veloGB10 - Rust and CUDA inference engine built only for GB10 with bitwise-lossless MTP, Qwen3.8-Flash-Next EXL3 at 137 tok/s on one machine and 221 on four, pure-code decode.
  • sixteen-miles-labs/sparklab - GB10-only inference runtime for one DGX Spark with NVMe-backed MoE expert banks, GLM-5.3 753B at 1.29 decode tok/s and DeepSeek V4.1 Flash 552B at 1.05, both experimental.
  • Th0rgal/dgx-spark-router - Stdlib-only OpenAI-compatible router that swaps six llama.cpp GGUF and vLLM NVFP4 models in and out of 128 GB unified memory, with Marlin GEMM defaults for GB10.
  • vcruz305/DeepSeek-V4.1-Flash-EXL3-DGX-Spark-recipe - DeepSeek-V4.1-Flash EXL3 1.59 bpw on one DGX Spark in native ExLlamaV3 with the DSpark drafter aliased from mmap over ATS, 17.5 tok/s median on fresh prompts.
  • xangel82/DS4-GB10-GX10-DSpark-CUDA - DS4 fork for DeepSeek-V4-Flash on one GB10, lossless DSpark and HybridLC decode at 24-26 t/s on tool calls against the original 13, 900-953 t/s prefill.

Fine-tuning

Quantization & NVFP4

GB10's Blackwell architecture supports NVFP4 (4-bit floating point) in hardware. It runs faster than INT4 at similar quality.

Models & Benchmarks

  • albond/DGX_Spark_Qwen3.5-122B-A10B-AR-INT4 - Qwen3.5-122B-A10B on DGX Spark, tuned from 28.3 to 52 tok/s (+82%) with a hybrid INT4+FP8 checkpoint and an INT8 LM head.
  • Avarok-Cybersecurity/atlas-recipes - Recipe corpus for Atlas on GB10, run by the atlasctl launcher that replaces sparkrun, with per-model KV dtype and MTP width.
  • Blackwellboy/laguna-s21-lab - Laguna S 2.1 NVFP4 testing lab on one DGX Spark, 20-cell tuning sweep with its losing cells, 12-hour soak of 3,096 turns, and 450-turn thinking-gate study.
  • colonel-otto/3x-dgx-spark-mesh-deepseek-v4-0731-flash - DeepSeek-V4-Flash at TP=3 on three DGX Spark, decode 6.7 to 20.2% faster than two nodes at n=30 on the retired Anemll engine, 84.7 tok/s c1 on eugr's b12x image.
  • DanTup/spark-evals - Harbor-run leaderboard of evo eval, aider polyglot, and swe-rebench scores under Codex and Terminus-2 agents for four model configurations that fit on one DGX Spark.
  • DG1001/local-agentic-coding-128gb - Coding-agent benchmark of 14 local models on one ASUS Ascent GX10 under three harnesses, 86 hidden tests, with Nemotron scoring 47 to 85 across 13 runs.
  • elsung/dgx-spark-deepseek-v4-flash - DeepSeek-V4-Flash official FP8 across two DGX Spark under vLLM TP=2 over a 200 Gb/s QSFP56 RoCE cable, 41 tok/s single stream and ~350 aggregate at c=32.
  • Entrpi/ds4-on-spark - DGX Spark fork of antirez/ds4 at 2.4-3.3x upstream prefill and 1.33-1.47x decode, 59 tok/s over 12 concurrent requests, and 2.26M tokens of active context at shipped defaults.
  • Entrpi/qwen3.5-122B-A10B-on-spark - Qwen3.5-122B-A10B on a single DGX Spark via DFlash block-diffusion spec-decode, 81 tok/s on agent traffic.
  • evanwtf/local-llm - Coding-agent benchmark of model, engine and harness stacks on a two-node DGX Spark cluster, ranked by suite pass rate then wall time, 29 configurations under OpenCode.
  • GaelicThunder/colibri-gb10-attention-cliff - Fixed-size kernel guard at 8192 context tokens in colibri on GB10, silent CPU fallback at 0.45 versus 0.86 tok/s, plus per-branch counters and a sweep harness.
  • GaelicThunder/DeepSeek-V4-Flash-Vision-One-DGX-Spark - DeepSeek-V4-Flash-Vision-Exp in EXL3 on one DGX Spark at 245,760 context, 37.6 tok/s on code with images in the same process, keeping 90% of the original token probability.
  • GaelicThunder/gb10-uma-inference-notes - Five measured GB10 unified-memory properties that hold across models and engines, including host-to-device copies as pure waste worth 63% once removed.
  • GaelicThunder/moe-offload-findings - Nine findings on MoE decode with experts streamed from NVMe, mostly negative: batching does not amortize expert reads and prefetching cannot beat a static pin.
  • gitcommit90/qwen38-27b-dgx-spark - Qwen3.8-27B NVFP4 on one GB10 with Inco DFlash 2 speculative decoding, 44.46 tok/s versus DSpark 31.95 at k=7, plus a BF16 lm_head guard fix.
  • hebo1221/motif3-dgx-spark - Motif-3 315B as mixed IQ2_XXS on one DGX Spark, 83.56 GiB at 16.49 tok/s, published with the author's verdict that the quant misses BF16 quality retention.
  • jeremy-newhouse/dgx-spark-nemotron-super-bench - Single-stream decode benchmark of Nemotron-3-Super-120B-A12B-NVFP4 on one GB10, ~26-27 tok/s realistic with MTP vs ~33.6 microbench.
  • jiayuqi7813/DeepSeek-V4-Flash-0731-CRACK-2x-DGX-Spark - Rank-1 Householder refusal edit of DeepSeek-V4-Flash-0731 in native FP8 UE8M0 blocks on two DGX Spark, compliance 3.53 to 90.59% with HumanEval 148 against 150.
  • jvr0x/dgx-spark-bench - Closed-loop concurrency sweeps on DGX Spark with pinned recipes and a GitHub Pages dashboard, per-session and aggregate tok/s across 43 published runs.
  • k3net/docai-evals - Evidence repository for 19 Hungarian document-AI and GB10 serving experiments, where Marlin beats the publisher-recommended MoE backend by up to 3.3x and NVFP4 roughly doubles counterparty-role errors.
  • Kleybrink/dgx-spark-bench - Ollama benchmarking framework for DGX Spark measuring throughput, latency, memory, and answer quality with an LLM-as-a-judge pipeline over 21 prompts in 9 categories.
  • marksunner/dgx-spark-single-stack - Single-box agent stack on DGX Spark, Hermes runtime and Honcho memory on CPU beside vLLM serving Qwen3.5-122B hybrid INT4+FP8 with MTP at 41-47 tok/s.
  • marksunner/dgx-spark-step37-flash - StepFun's Step 3.7 Flash (198B MoE) on a single DGX Spark with llama.cpp at ~27 tok/s and 96K context on a q8_0 KV cache, reduced from 128K for CUDA-graph stability.
  • martimramos/dgx-spark-ml-guide - Troubleshooting playbook for PyTorch on GB10, 16 numbered failures with an error-to-fix table, from cu128 nightly wheels to aarch64 mmcv builds and NVRTC symlinks.
  • Memoriant/dgx-spark-kv-cache-benchmark - KV cache quantization on GB10: q4_0 costs 37% of generation throughput at 110K context, TurboQuant turbo3 up to 23.6% at 32K, and prompt processing is untouched.
  • mneha05/gb10-attn - Context-split FlashDecoding paged-attention decode kernel at 82-85% of GB10's 273 GB/s on large working sets, fp16 gpt2 geometry, after correcting a 2x roofline and an L2-cached benchmark.
  • msuiche/weightless - Serve-time refusal steering with GGUF layer-projection vectors instead of redistributed weights, validated on Qwen3.8-27B on one DGX Spark and GLM-5.3-Flash on four.
  • nabe2030/dense-27b-31b-dgx-spark - Dense Qwen 3.5/3.6-27B and Gemma 4-31B on llama.cpp b8922, Q4_K_M at 10-12 tok/s versus 3.8-4.5 BF16, JCommonsenseQA cost 0.2-0.6 points.
  • nabe2030/gemma4-vs-qwen35-dgx-spark - Gemma 4 26B-A4B versus Qwen 3.5/3.6-35B-A3B MoE on llama.cpp, F16 thinking-mode bug isolated, 26.5 against 58 tok/s decode and 0.35 point JCommonsenseQA spread.
  • OscarActual/gb10-llm-benchmark - Ollama benchmarks for GB10 across 11 LLMs and 10 embedders: decode tok/s, TTFT, and Czech RAG recall.
  • pendakwahteknologi/gx10-benchmarks - Benchmark roster for the ASUS Ascent GX10 (GB10) with nine published runs across inference, training, efficiency, and generation, each carrying timestamped CSV and log artifacts.
  • r0b0tlab/deepseek-v4-flash-nvfp4-gb10-benchmark - DeepSeek-V4-Flash FP8 on two DGX Spark at TP=2 with MTP over RoCE, 38.4 tok/s c1 and 144.6 aggregate at c16 on driver 580.142, down about 3.5x on 580.159.03.
  • r0b0tlab/diffusiongemma-26b-nvfp4-sm121-vllm - DiffusionGemma 26B-A4B NVFP4 under vLLM on GB10 with the FlashInfer CUTLASS FP4 MoE path, 146.3 tok/s at c1 and 242.9 at c16, no Marlin fallback.
  • r0b0tlab/laguna-s-2.1-nvfp4-sm121-vllm - Laguna S 2.1 NVFP4 on GB10 under vLLM 0.25.1, DFlash K=7 at 22.2 tok/s c1 with thinking off on revision 0761412, plus an 8,620-case scorecard for the earlier 216d1f1.
  • r0b0tlab/nex-n2-mini-nvfp4 - NVFP4 vLLM container for Nex-N2-mini (Qwen3.5-MoE-35B) on GB10, 185 tok/s aggregate at concurrency 8.
  • r0b0tlab/step37-flash-nvfp4-sm121-vllm-docker - vLLM container for StepFun's Step 3.7 Flash NVFP4 (198B MoE VLM) on dual GB10 TP=2, with verified native-CUTLASS sm_121 execution at 16.49 tok/s.
  • ramsred/llm-engine-benchmark - Long-context comparison of vLLM, SGLang, and TensorRT-LLM on GB10 under one client, plus a prefill-budget study cutting P95 TTFT 26.9% by moving 8192 to 2048.
  • styles01/sparkrun-recipes - Source-pinned SparkRun recipes for nine exclusive lanes on one GB10, led by a Qwen3.8-Flash-Next EXL3 native-MTP daily driver at 54.3 tok/s single-stream decode.
  • ThinkCode/glm53-flash-2x-gb10-bench - GLM-5.3-Flash NVFP4 against EXL3 on two GB10, with NVFP4 ahead cold at every concurrency and EXL3 ahead 1.6x at warm C4 on prefix-cache reuse NVFP4 never gets.
  • VincentMarquez/glm52-gb10-colibri - GLM-5.2 744B on one DGX Spark at full top-8 via a colibri engine branch, 11.1 tok/s on a synthetic prompt with PLD, 5-7 on real chat.
  • Weschera/spark-bench - LLM benchmark for DGX Spark across 80 scenarios in 13 domains, with 12 multi-turn agentic workflows, 4 machine-graded long-generation builds, and a TrueScore weighting speed at 5%.

Multi-node

You can connect two DGX Spark units directly over 200 Gb/s QSFP for double the memory and compute.

  • 0xdfi/GLM-5.2-1M-4x-DGX-Spark - Profile index for unpruned GLM-5.2 744B on 4x DGX Spark with NVFP4 DS-MLA KV, O14 Fast at 250K total KV, 819 tok/s prefill, 42.3 peak decode.
  • 0xdfi/GLM-5.2-R9-Adaptive-MTP-FULL-CUDA-4x-DGX-Spark - GLM-5.2 on four DGX Spark nodes with FULL CUDA graphs for every adaptive MTP depth K2/K4/K5, 83.4 tok/s at C4 measured before the 420K retune, 520K balanced profile.
  • 0xSero/glm-5.3-flash-sglang-sm121 - GLM-5.3-Flash NVFP4 under SGLang on two or four DGX Spark, 22.69 tok/s single stream and 82.37 at eight on TP=4, digest-pinned with an acceptance checklist.
  • ajensenwaud/Kolibri-1-2x-DGX-Spark-TensorFold - Kolibri-1 on two DGX Spark under TensorFold with 17 patches over PR #328, 83.7 tok/s single-stream decode at FP8 against 47.1 on one Spark.
  • alexellis/glm-5.3-flash-4x-dgx-spark-switchless - GLM-5.3-Flash NVFP4 at TP4 across four DGX Spark cabled as a switchless RoCE ring, ~45 tok/s on agentic traffic over patched NCCL 2.30.7 that skips the wedging tree connect.
  • ArgentAIOS/dgx-spark-cluster - Two-node DGX Spark guide with DMA-BUF NCCL settings for GB10 where nvidia-peermem GPU Direct fails, 93.5% DDP scaling on a 200 Gb/s RoCEv2 link.
  • bertholomus/deepseek-v4.1-tensorfold-tp2-2xgb10 - DeepSeek-V4.1-Flash EXL3 2.9 bpw on two DGX Spark under a TensorFold TP2 engine with DSpark drafting, 1,048,576-token window at four streams, 100.5 tok/s greedy single-stream code.
  • bird/GLM-spark - GLM-5.2 across four DGX Spark nodes, 1M context at 24.7 tok/s on unpruned Int4-Int8Mix weights, TP4 plus DCP4 KV sharding and lossless speculative decoding.
  • botAGI/dspark-0731-gb10 - DeepSeek-V4-Flash-0731 on two DGX Spark under vLLM 0.25.2, flashinfer_b12x MoE backend worth 9-12% step rate to 256K, 28 tok/s single stream at 1,042,600 tokens.
  • bumasoft/Qwen3.8-Flash-Next-TP3-DGX-Spark-VLLM - Qwen3.8-Flash-Next FP8 across three DGX Spark at tensor-parallel 3, checkpoint padded in place at 60.9 tok/s, where padding key heads alone silently breaks the 1:3 GDN pairing.
  • chadhurley25075-png/pd-bridge - DeepSeek-V4-Flash prefilled on two DGX Spark, decoded on a Mac Studio over plain 10 GbE with no shared cache format, 3.7x vs the Mac alone on a 241K cold prompt.
  • chishiki37/dgx-spark-fabric - Switched MikroTik CRS812 fabric replacing the direct DAC between two DGX Spark nodes, fixing broken RoCE for 26-33% more decode, with 100 and 200 Gb/s breakouts measured identical.
  • christopherowen/dgx-spark-networking - Switchless RoCE collectives library for DGX Spark rings, one-shot BF16 all-reduce at 16.9 µs against NCCL's 90.6 to 92.4 µs for 10 KiB on four nodes.
  • christopherowen/spark-ds41f - DeepSeek-V4.1-Flash on three switchless DGX Spark at TP3 with TileLang sm_121 kernels, 52.2 prose and 63.0 code tok/s single stream at 512K context.
  • ciprianveg/gb10-vllm - Model-agnostic sm_121 vLLM platform, KIMI-K3 v5 at TP16 plus DCP8 with RoCEnante collectives on 16 GB10, 29.81 tok/s at C1 and 87.12 aggregate at C8, GLM-5.3 on GLM-5.2's v19 image.
  • CosmicRaisins/glm-5.2-gb10 - Unpruned GLM-5.2 Int4-Int8Mix on four GB10 nodes with DCP KV sharding, 320K context at 598 t/s prefill or 640K at 430, decode flat near 22 t/s.
  • CosmicRaisins/minimax-m3-awq-gb10 - MiniMax-M3-AWQ-INT4 vLLM serve recipe for 4x GB10, FP8 KV cache, EAGLE3 spec-decode, and indexer-corruption fix.
  • digchick/dgx-spark-200g-link-fix - Troubleshooting playbook for the 200G ConnectX-7 link failing to train between two Sparks (CX7 hotplug power-saving), with the fix and NCCL/RoCE verification.
  • drowzeys/keys-1M-CTX-Inkling-Small-NVFP4-Dspark-NVFP4-KV-Cache-SGlang-SM121-optimized-on-Two-DGX-Sparks - NVFP4 KV cache in the SGLang triton backend for Inkling-Small on two DGX Spark, 3.12x pool for 1M context, 23.9 tok/s on a pooled open-ended mix.
  • drowzeys/keys-MiMo-V2.6-Pro-MOPD-C3-Jarrelscy-ARVQ-4-DGX-Sparks-1M-Context - MiMo-V2.6-Pro-MOPD in Jarrelscy's ARVQ and NVFP4 hybrid on four DGX Spark at TP4 and 1M context, single-stream 32.2 tok/s on code and 24.2 on prose with MTP k=2.
  • drowzeys/Keys-Setup-Autonomous-Self-Improving-Local-Inference-Stack - Mixture-of-Agents stack for four DGX Spark nodes with a DeepSeek-V4-Flash router and an NVFP4 Two-Tower consolidated onto one node at 29 tok/s.
  • drowzeys/keys-TensorFold-GLM-5.3-TP4-4x-DGX-Spark - GLM-5.3 753B at EXL3 2.75 bpw on four DGX Spark under TensorFold TP4 with MTP 2, 40.2 tok/s prose with thinking on, needle found at 905,182 tokens.
  • Enntity/sparkglm - GLM-5.3-Flash NVFP4 on two DGX Spark under the Atlas engine with DFlash2 and prefix caching, 0.67 s median first token on turns 2+ of 30-48K conversations.
  • epappas/gx10-cluster - Ansible provisioning for a GB10 cluster over ConnectX-7 with diagnostic tools, a recipe catalogue, and measured-or-forum-read labels on hardware claims, 22.7 GB/s two-node NCCL busbw.
  • FujitsuPolycom/sparkring - One-command installer and vLLM/SGLang serving for switchless two- or four-Spark GB10 rings, using RoCEnante RDMA collectives for decode and NCCL 2.32.3 for larger ones.
  • HeNryous/mimo-v25-dflash-dgx-spark - MiMo-V2.5 (309B MoE, NVFP4 plus a required MXFP8 o_proj overlay) on two DGX Spark nodes, DFlash drafting ~54 tok/s on structured content, 1.67M-token fp8 KV pool at 500K.
  • idonati/spark-vllm-docker-festr2 - vLLM patches for festr2 MiMo-V2.5-Pro NVFP4/MXFP8 on an 8-node sm_121 cluster, fused-QKV fix for Q mis-slotted as K/V on 7 of 8 ranks, 114 tok/s aggregate at 20 concurrent.
  • jakejharris/jspark3 - GLM-5.3-Flash on three DGX Sparks with a TensorFold fork and DFlash2 drafting, RigMark estimates at reasoning effort low of 91.3 tok/s code, 51.6 prose, 2,124 tok/s cold 64K prefill.
  • jayleaton/glm53-tensorfold-spark - GLM-5.3-Flash abliterated EXL3 4-bit on two DGX Spark under TensorFold plus 77 patches, RigMark 57.5 tok/s at C1 and 95.1 at C4.
  • joesinvestments/DeepSeek-V4-Flash-0731-TP4-4x-DGX-Spark - DeepSeek-V4-Flash-0731 at TP=4 on four DGX Spark under vLLM 0.25.2 with DSpark k=7, 123.13 tok/s single stream at 2K tokens, 57.9 at ~150K agentic prompts.
  • joesinvestments/glm52-spark-kit - GLM-5.2 on four DGX Spark as source overlays over stock vLLM, fused nvfp4_ds_mla KV writer at 51 times the torch reference, sparse indexer unblocked above DCP 1.
  • joeynyc/Hy3-295B-NVFP4-2x-DGX-Spark - Tencent Hunyuan 3 295B MoE in NVFP4 at TP2 on two DGX Spark, 26 tok/s single stream at 262K with TurboQuant k8v4 KV, MTP measured 20% slower.
  • joeynyc/MiniMax-H3-2x-DGX-Spark - Cross-host diffusion executor for one MiniMax H3 video across two DGX Spark nodes, Ulysses sequence parallelism over RoCEv2, 68.8 s against 155.0 s single-box.
  • josephdrose/joe-spark-patches - Out-of-tree vLLM patches for DeepSeek on four DGX Spark, Engram kept on NVMe because cpu_offload frees nothing on GB10, plus a DSpark proposer that survives concurrent requests.
  • josephdrose/nccl-spark-switchless - NCCL 2.30.7 patches for a switchless 4-node GB10 RoCE ring, tree-skip plus 2-hop relay over the uncabled diagonals, MiniMax-M3 229B NVFP4 at ~24 tok/s.
  • karolpalys/glm52-triple-spark-tuning - Tuning log and negative results for GLM-5.2 753B on three DGX Spark nodes, with the measurement methodology and the evidence that killed each rejected change.
  • kindlingai/glm-5.3-flash-gx10 - GLM-5.3-Flash NVFP4 on two, three, four or six GB10 under vLLM with mentat in place of Ray, 117.3 tok/s code decode at TP=4 with DFlash2.
  • kindlingai/glm-5.3-full-exl3-tp6 - Full GLM-5.3 EXL3 3.25 bpw on six DGX Spark at TP6 by re-fragmenting experts without requantizing, 33.8 tok/s prose at MTP k=2, 958 tok/s prefill at 32K.
  • kingjones30/GLM-5.3-Flash-2x-DGX-Spark - GLM-5.3-Flash NVFP4 on two DGX Spark, NoPE latent padded to the rope width sm_121 kernels expect, 24.7 tok/s on code under MTP-5 on the stock image.
  • knapcio/DeepSeek-V4.1-Flash-4x-DGX-Spark-TP4 - DeepSeek-V4.1-Flash TP4 on four DGX Spark under SGLang with RoCEnante all-reduce, 89.7 tok/s prose and 131.9 code at c1 with the SM clock capped at 2200 MHz.
  • knapcio/GLM-5.3-Flash-4x-DGX-Spark-TP4 - GLM-5.3-Flash NVFP4 at TP4 on four DGX Spark with 8-bit dense layers and DFlash2, 90.3 tok/s prose single stream, 3,470 tok/s cold prefill at 32k.
  • Libertai/glm53-flash-vllm-gb10 - GLM-5.3-Flash under vLLM on two DGX Spark at 24.2 tok/s through a hand-written sparse-MLA kernel, with degenerate output traced to an uninitialized MoE activation scale.
  • magicbear/DeepSeek-V4.1-Flash-SGLang-DGX-Spark - DeepSeek-V4.1-Flash under SGLang on four against eight DGX Spark, c1 code decode 57.9 against 67.0 tok/s, 1.63-1.76x prefill at eight, while its own vLLM cross-check reaches 75.5 on four.
  • makiisthenes/dgx-spark-multinode-vllm-ray - Dual-DGX Spark vLLM deployment with NVIDIA vLLM 26.04, Ray, and 200 GbE QSFP.
  • maliubiao/dgx-spark-2-deepseek-flash-0731 - Bilingual manual for DeepSeek-V4-Flash-0731 and Vision-Exp on two DGX Spark, with LMCache v0.5.3 built on aarch64 for NVMe cold KV backup, 1 GiB L1, 500K context.
  • MiaAI-Lab/DeepSeek-v4-Flash-DSpark-2x-DGX-Spark - Two-node vLLM TP=2 recipe for DeepSeek-V4-Flash-Vision-Exp with native image input, DSpark speculative decode and nvfp4_ds_mla KV at a 1M-token ceiling.
  • MiaAI-Lab/DeepSeek-v4.1-Flash-DGX-Sparks - DeepSeek-V4.1-Flash under SGLang on three or four DGX Spark with NVMe-resident Engram tables, TP4 prose c1 87.7 tok/s on a switch, 1M-context needle passed at 1,011,084 tokens.
  • MiaAI-Lab/DeepSeek-v4.1-Flash-EXL3-2x-DGX-Sparks - DeepSeek-V4.1-Flash at 2.9 bpw EXL3 on two DGX Spark with vLLM TP2 and file-backed Engram, 31.6 tok/s single stream with DSpark k=3, 600K context.
  • MiaAI-Lab/GLM-5.2-NVFP4-AQLM-Triple-DGX-Sparks - GLM-5.2 NVFP4 plus AQLM 2-bit hybrid on three DGX Spark at TP3, 21 tok/s structured at 348K vision context with top-4 routing, 25-26 on fp8 KV at 235K.
  • MiaAI-Lab/GLM-5.3-EXL3-3x-DGX-Sparks-TensorFold - GLM-5.3 EXL3 2.75 bpw on three DGX Spark under TensorFold, a 499,712-token window by context parallelism, 41.7 tok/s code, a 94K prompt resumed from NVMe in 3.0 s.
  • MiaAI-Lab/GLM-5.3-Flash-EXL3-2x-DGX-Sparks-TensorFold - GLM-5.3-Flash EXL3 on two DGX Spark under TensorFold v0.6.0 with 96 patches, 1,048,576-token window at 4 concurrent requests, 60.4 tok/s prose and 114.7 structured at c1.
  • MiaAI-Lab/GLM-5.3-Flash-NVFP4-Dual-DGX-Spark - GLM-5.3-Flash NVFP4 on two DGX Spark over Ray TP=2 with image and video input, MTP at four draft tokens, FP8 KV cache and 262K context.
  • MiaAI-Lab/Inkling-Small-NVFP4-Dual-DGX-Sparks - Inkling-Small-NVFP4 across two DGX Spark on SGLang at a 1,142,712-token KV pool, 33.9 tok/s single stream, page size 1 required for the triton DSpark verify path.
  • MiaAI-Lab/MiMo-V2.6-Flash-2x-DGX-Sparks - MiMo-V2.6-Flash MXFP4 under SGLang on two DGX Spark, DFlash at 69.8 tok/s on code and EAGLE MTP at 35.0 on prose, single stream.
  • MiaAI-Lab/Qwen3.8-Flash-Dual-DGX-Sparks-TensorFold - Qwen3.8-Flash-Next NVFP4 on two DGX Spark under TensorFold's Zig engine at TP2 with FP8 KV, 1,048,576-token window, 67.4 tok/s prose at c1 and 390.1 at c16.
  • MiaAI-Lab/Qwen3.8-Flash-Next-Dual-DGX-Sparks - Qwen3.8-Flash-Next NVFP4 on two DGX Spark under vLLM TP2 with expert parallel and MTP-3, 56.8 tok/s prose at one stream and 225 aggregate at eight with 47k draft vocabulary.
  • nabe2030/dgx-spark-2node-rpc - GLM-5.2 GGUF at 228.5 GB split across two DGX Spark nodes over llama.cpp RPC, CX7 measured as two ~100 Gb/s PCIe Gen5 x4 paths, RDMA vs TCP A/B.
  • nacyot/vllm-ds4f-gb10 - vLLM fork for DeepSeek-V4.1-Flash on four GB10 at TP=4 with disk KV offload, a 493K-token session restored from SSD in 7.8 s against a 392 s cold prefill.
  • neko-legends/spark-bench - Four DGX Sparks as one TP4 cluster over six dated model lanes, the live one DeepSeek-V4.1-Flash uncensored on TensorFold at 66.5 tok/s prose and 104.1 code, 1k-160k prompts.
  • ondigo-winder/SWITCHLESS-NCCL-RING-4-GB10 - NCCL 2.30.7 patch for a switchless four-node GB10 ring using both PCIe halves of each QSFP cable, 193.1 Gb/s all-reduce bus bandwidth against 111.6.
  • OsakaTX/qwen3.8-flash-next-vllm-dgx-spark - Qwen3.8-Flash-Next NVFP4 on two DGX Spark under vLLM TP2 with MTP n=3, 41-44 tok/s c1 and 162 aggregate at eight, RDMA passthrough worth 40-45%.
  • pfn/spark-vllm-compose - Head and worker Docker Compose files that run vLLM across DGX Spark nodes with native --nnodes/--node-rank instead of Ray, shipped services for Qwen3.5-397B-A17B-int4 and MiniMax-M2.7.
  • r0b0tlab/DeepSeek-V4-Flash-DSpark-v026-SM121 - Dual-GB10 DeepSeek-V4-Flash-0731 on vLLM 0.26 with a digest-pinned GHCR image and runtime gate, NIAH PASS at 1M, BFCL multi_turn_base 0.755, ~79 tok/s c1 decode.
  • r0b0tlab/qwen38-flash-next-w4a16-sm121-sglang - Qwen3.8-Flash-Next self-quantized to NVFP4 W4A16 on two GB10 under SGLang TP=2 with NEXTN MTP, 63.84 tok/s at c1 and 132.64 at c4 on 1,024-token prompts.
  • rajsinghtechbot/dgx-spark-vllm-k8s - Kubernetes cookbook for DeepSeek-V4-Flash on dual DGX Spark, with Multus/Spiderpool RDMA over RoCEv2, UMA-aware container memory limits, and Prometheus monitoring.
  • raullenchai/twinspark - Self-healing two-node vLLM cluster for DeepSeek-V4-Flash-0731 on DGX Spark at 74.8 tok/s, needle sweep cutting long-context failures from 8/25 to 2/25 by trading nvfp4_ds_mla KV for fp8_ds_mla.
  • Reederey87/dgx-spark-2x-deepseek-v4-flash - DeepSeek-V4-Flash-0731 on two DGX Spark from a full-source vLLM main build, four gated one-file upstream fix layers promoted on Welch non-inferiority, 3,027,217-token KV pool.
  • Reederey87/glm53-flash-exl3-2x-dgx-spark - GLM-5.3-Flash EXL3 on two DGX Spark at 1M context, 110k replay prefix-cache hits lifted from 0 to 97-98% by 3,584-token batches plus a drafter-prune patch.
  • RustRunner/DGX-Llama-Cluster - Three DGX Spark nodes as a switchless ConnectX-7 RDMA star running llama.cpp RPC, 384 GB pooled unified memory for 400B+ models in 4-bit, NFS model share.
  • sfxnz/DeepSeek-V4-Flash-Vision-Exp-vLLM-2x-DGX-Spark - DeepSeek-V4-Flash-Vision-Exp on two DGX Spark at TP=2, ViT loaded as a vLLM plugin that preserves DSpark-6 draft acceptance, 26.2 tok/s prose single stream at 1M context.
  • strusty/GLM-5.3-Flash-NVFP4-3x-DGX-Sparks-kindling-DGXOS - GLM-5.3-Flash NVFP4 at TP=3 on three DGX Spark in a switchless triangle on stock DGX OS, 3,054,135-token KV pool, about 3,500 tok/s cold prefill at 64k.
  • tomsti/guides - GB10 cluster guide for DGX Spark over ConnectX-7 RoCE, covering NCCL rail pinning, the duplicate-MAC workaround, and MikroTik 400G switching.
  • tonyd2wild/DeepSeek-v4-Flash-Vision-Exp-DSpark-1M-NVFP4-KV-2x-DGX-Spark - DeepSeek-V4-Flash-Vision-Exp ported into vLLM on two or four DGX Spark at 1M context, 53 tok/s real-prompt decode single stream and a 2.79M-token NVFP4 KV pool at TP2.
  • tonyd2wild/DeepSeek-V4.1-Flash-vLLM-DGX-Spark - DeepSeek-V4.1-Flash on four DGX Spark at TP4 with Engram rows read from NVMe, 3.5 bpw EXL3 serving lane at 95.3 tok/s idle code and 500K context.
  • tonyd2wild/DS4-H3-Video-Gen-Factory - DeepSeek-V4-Flash at 1M context beside two MiniMax H3 video renders on two DGX Spark, 35% of idle throughput kept, and a load order set by H3's 50 GB footprint.
  • tonyd2wild/GLM-5.2-655K-MTP-4x-DGX-Spark---25-32tok-s - GLM-5.2 744B unpruned (QuantTrio Int4-Int8Mix) at 655,360-token context across four DGX Spark nodes via decode-context-parallelism, 23.0 tok/s single and 47.9 aggregate at 4 concurrent, MTP k=3.
  • tonyd2wild/GLM-5.2-QuantTrio-200K-4x-DGX-Spark--36tok-s - Speed-shape recipe for unpruned GLM-5.2 at 200K context on four DGX Spark nodes, 36 tok/s peak, 75 aggregate at 6 concurrent, 63% of each step overhead.
  • tonyd2wild/GLM-5.3-Flash-NVFP4-DFlash2-2x-DGX-Spark - GLM-5.3-Flash NVFP4 on two DGX Spark with knapcio's TP4 stack ported to TP2 and DFlash2, single-stream code decode 68.9 tok/s against 44.7 for the previous recipe at 262K context.
  • tonyd2wild/GLM-5.3-Int4-Int8Mix-TP4-4x-DGX-Spark - GLM-5.3 743B Int4-Int8Mix at TP4 on four DGX Spark, DFlash2 at 53.32 tok/s structured output (1.98x MTP-4, level on prose), NVFP4 KV pool of 293,447 tokens at 270K.
  • tonyd2wild/MiMo-V2.5-TP2-1M-NVFP4-KV-2xDGX-Spark - MiMo-V2.5 Omni at tensor-parallel 2 on two DGX Spark, NVFP4 4-bit KV cache for a 2.17M-token pool at 1M context, thinking-OFF eval 97.8 against 90.6.
  • tonyd2wild/MiMo-V2.5-TP3-NVFP4-KV-3xDGX-Spark - MiMo V2.5 Omni (310B MoE, text/image/video/audio) at tensor-parallel 3 across three DGX Sparks, with 4-bit NVFP4 KV cache for a ~10.6M-token KV pool at 1M context.
  • tonyd2wild/MiMo-V2.6-Flash-DGX-Spark-Recipe - MiMo-V2.6-Flash-RL on two DGX Spark under vLLM TP2 with DFlash and fp8 KV, 53.3 tok/s single stream under a 300K limit, after four patches to the stock image.
  • tonyd2wild/MiniMax-M3-2x-DGX-Spark-36-tok-s - Reproduction of a3refaat's MiniMax-M3 428B unpruned stack on two DGX Spark, W4A16 GPTQ with NVFP4 KV and EAGLE-3 at 36.6 tok/s single-stream JSON and 31.8 code, 196K context.
  • tonyd2wild/Minimax-M3-NVFP-3x-DGX-Sparks-TP-3 - MiniMax-M3 NVFP4 428B-A23B at tensor-parallel 3 across three DGX Sparks, 10.5 tok/s at 200K context over a switchless 200 Gb/s RoCE mesh.
  • tonyd2wild/nfs-model-weights - NFS recipe for sharing one checkpoint across N DGX Spark nodes, taking a 4-node model library from 6.8 TB to 1.7 TB with no per-node copies.
  • tonyliu312/GLM-5.3-Flash-1M-Context-4x-DGX-Spark - GLM-5.3-Flash at 1,048,576-token context on four DGX Spark, 2.67x decode from dropping --enforce-eager and 1M concurrency from 1.35x to 4.20x by raising --kv-cache-memory, which silently overrides --gpu-memory-utilization.
  • tpurtell/glm-5.2-4x-spark-1x-rtx6k-96gb - Rust attention-FFN disaggregation engine for GLM-5.2 on one RTX PRO 6000 coordinator and four DGX Spark expert nodes, 26.6 NVFP4 and 28.5 EXL3 K3 tok/s weighted decode, 1,807 prefill.
  • tsarihan/qwen3.8-flash-next-nvfp4-2x-dgx-spark-playbook - Qwen3.8-Flash-Next NVFP4 against FP8 on the same two DGX Spark, 3.67x the KV pool and 66% more decode at 245K, needles 5/5 on both lanes.
  • urbanspr1nter/dgx-spark-bare-metal - Four-node DGX Spark Ray and vLLM cluster on a Mikrotik switch, with an 8-node guide on 400 Gb/s breakout cables, plus GLM-5.2 NVFP4, Kimi K2.7 Code and DeepSeek-V4-Flash launchers.
  • ursuciprian/qwen3.8-flash-next-dgx-spark-tp-2 - Qwen3.8-Flash-Next NVFP4 on two DGX Spark under vLLM V2 with b12x kernels, where one replica per node behind a router finishes synthetic agent replays 29-37% sooner than TP=2.
  • vroomfondel/dgxarley - Ansible playbooks for a K3s cluster of four DGX Spark nodes and an x86 control plane, SGLang over SR-IOV RoCE at 9.78 GB/s NCCL bus bandwidth.
  • Weschera/Ling-3.0-flash-VL-2x-DGX-Sparks - Ling-3.0-flash-VL FP8 on two DGX Spark under SGLang TP2 at 131,072 tokens, 26.0 tok/s single-stream on prose and 18.5 on code, with no MTP head.
  • www-ai-rs/gb10-deepseek-v4-flash - Two-node GB10 operator tooling and executed-code test harness for DeepSeek-V4-Flash 304B at 1M context, GPU rail power sampled at 2 Hz.
  • yunwei37/dgx-spark-4-ring-no-switch - Serving profiles and results log for four DGX Spark on a switchless ConnectX ring, DeepSeek-V4.1-Flash TP4 at 1M context 50.14 tok/s C1, gmu 0.88 recorded as unsafe.
  • ZD-AI-Lab/Triple-GB10 - Three-node GB10 QSFP ring with three /30 subnets and forwarding routes, pooling about 300 GB for Ray and vLLM pipeline-parallel across 3 Sparks.
  • zorost/sparkduet - Model-swap layer for two DGX Spark, four checkpoints on disk behind one OpenAI port, DeepSeek-V4-Flash c1 from 72.2 tok/s on math to 33.6 on prose by DSpark draft acceptance.

Image & Media Generation

  • AEON-7/comfyui-aeon-spark - ComfyUI Docker for DGX Spark with SageAttention v3 compiled for sm_121a, CUDA 13, NVFP4, and Flux 2 / LTX 2.3 pre-bundled.
  • alexhegit/h3-spark.c - CUDA port of antirez/h3.c for MiniMax-H3 on GB10, 15.6 s warm for a 512x512 22-frame clip at layers 45 and reuse 2.
  • bjarkebolding/spark-comfyui - Single-script containerized ComfyUI for DGX Spark, sm_121 SageAttention and sha256-verified workflow recipes, with a 2100 MHz clock cap for overcurrent reboots.
  • CoconutMacaroon/blender-arm64 - Blender build for GB10 aarch64 with CUDA, OptiX, and Vulkan, shipping a prebuilt DGX Spark binary release.
  • dr-vij/ComfyUI-DGX-Spark-Docker-opinionated - ComfyUI Docker for DGX Spark with self-built aarch64 wheels for decord NVDEC, flash-attn, onnxruntime-gpu and SageAttention 2.2.0, plus a SAM3 blacklist for WanVAE hangs.
  • dr-vij/Hunyuan3D-2.1-DGX-Spark-Docker - Hunyuan3D-2.1 3D generation on DGX Spark via Docker Compose, building custom_rasterizer and DifferentiableRenderer CUDA components on-box.
  • dr-vij/Trellis2-DGX-Spark-Docker - Dockerized TRELLIS.2 3D generation for DGX Spark, with nvdiffrast, CuMesh, FlexGEMM, and torchvision built from source for sm_121 on CUDA 12.9.
  • drowzeys/keys-SM121-Optimized-MiniMax-H3-Nvidia-Sol-Engine-Kijai-SolAttn_Triton-Single-DGX-Spark - MiniMax H3 in ComfyUI on one DGX Spark with flex_attention forced to Triton where sm_121 miscompiles it, plus Sol-Engine FirstBlockCache and batched VAE ports at 1.54x end to end.
  • Hitheshkaranth/LTX-2.5_Video_DGX_Spark_Setup - LTX-2.5 NVFP4 text and image-to-video with audio on DGX Spark via a three-line sm_121a kernel patch, 768x512 4 s clip in 61 s.
  • jayleaton/localrouter - MCP and OpenAI-style server that loads Qwen-Image 2.1 and MiniMax H3 on demand with Zig engines on DGX Spark, 1024x1024 NVFP4 in 12.7 s warm.
  • joeynyc/cosmos-locateanything-dgx - Two-stage DGX Spark pipeline: Cosmos 3 video generation, then NVIDIA LocateAnything object grounding.
  • joeynyc/MiniMax-H3-DGX-Spark - MiniMax H3 FL2VA video generation on one DGX Spark via vLLM-Omni and online FP8, sm_121 loader and AdaLN patch, 111 s warm request or 80 s with Cache-DiT.
  • kabilankb/cosmos3-nano-gb10 - Cosmos3-Nano 16B video and image generation on a single GB10 instead of NVIDIA's recommended 8x H100, 480p 57-frame clips in about 3 minutes.
  • LectinDK/DGX-Spark-ComfyUI-Forge - ComfyUI Docker for DGX Spark, xformers CUTLASS off on sm_121, and a --disable-pinned-memory fix that holds DynamicVRAM at a 73-78 GB peak against 88.
  • luix93/DGX-Spark-ComfyUI - ComfyUI Docker Compose for DGX Spark with SageAttention 2 built against sm_121, NVFP4 via comfy_kitchen, and a copy=False patch for the unified-memory double-VRAM bug.
  • madeye/comfyui-minimax-h3-dgx-spark - MiniMax-H3 video and audio in ComfyUI on GB10 sm_121 with 4-to-8-step turbo LoRAs, where fp8_scaled runs 21% faster than the recommended int8_convrot at 11.50 against 14.26 s/it.
  • mmartial/ComfyUI-Nvidia-Docker - Multi-platform ComfyUI Docker (x86_64, Blackwell, DGX Spark) with published aarch64 DGX images and userscripts that build SageAttention 2 and comfy_kitchen from source.
  • mvalancy/blender-nvidia-gb10 - Blender 5.0.1 source build for GB10 with Cycles CUDA 13 GPU rendering, via four inherited aarch64 patches and four CUDA-13 patches for OIDN, libglu, Wayland, and libdrm.
  • phaserblast/ComfyUI-DGXSparkSafetensorsLoader - Zero-copy model loader for ComfyUI on DGX Spark using the fastsafetensors library.

Audio & Speech

  • AEON-7/qwen3-asr-server - OpenAI /v1/audio/transcriptions server for Qwen3-ASR-0.6B on DGX Spark, vLLM-native with a pinned flashinfer and a soundfile decode path that avoids the PyAV fallback.
  • briancaffey/nemotron-asr-server - OpenAI-compatible speech-to-text server for nemotron-3.5-asr-streaming-0.6b on DGX Spark, native NeMo instead of the aarch64-broken Riva path, WebSocket streaming.
  • jxlarrea/homeassistant-voice-recipes - Local Wyoming voice pipeline for Home Assistant, aarch64 ONNX Parakeet ASR, ECAPA-TDNN speaker extraction, and Gemma-4-26B-A4B with MTP on llama.cpp built for sm_121.
  • kedarpotdar-nv/spark-realtime-chatbot - On-device assistant for voice and video calls on one GB10, ~320 ms and ~850 ms end to end, using Qwen3-VL, Kokoro, and DeepFace.
  • Logos-Flux/spark-voice-pipeline - WebSocket voice assistant for DGX Spark, sentence-level streaming across whisper.cpp, Ollama, and VibeVoice-Realtime-0.5B, 766 ms to first audio.
  • luka-loehr/qwen3-tts-native - Native Rust and CUDA runtime for Qwen3-TTS-1.7B VoiceDesign on sm_121, 94-96 ms p95 first audio and 5.68 GB peak versus 2.69 s and 108.90 GB for stock SGLang.
  • mARTin-B78/dgx-spark-faster-qwen3-tts - Faster-Qwen3-TTS on DGX Spark as an OpenAI-compatible API with CUDA-graph acceleration, four backends including chunk-streaming, and deterministic per-voice seeds.
  • Mekopa/whisperx-blackwell - Prebuilt WhisperX image with an sm_121 to sm_90 capability spoof and torchaudio jiterator patch, GPU pyannote diarization, 24 min audio in 62 s.
  • ncannings/fastconformer-trt - FP8 TensorRT engine for NeMo FastConformer ASR, parakeet-ultra at 4,903x real time and 1.814% test-clean WER on DGX Spark, against 999x and 1.803% for stock NeMo.
  • pipecat-ai/nemotron-voicechat-dgx-spark - Full-duplex speech-to-speech NemotronLabs VoiceChat 11B on one DGX Spark, GPTQ W8 Nano and W8A32 EarTTS at ~66 ms against the 80 ms frame budget.
  • Pizzaman213/fish-s2pro-gb10 - GB10-tuned Fish Audio S2-Pro TTS reaching 31.3 tok/s from 1.2 via bit-exact int8 kernels, speculative decode, and quality-gated NVFP4 weights.
  • WillIsback/whisperx-gb10 - WhisperX transcription and pyannote diarization REST API for GB10 (aarch64, sm_121), with an async job queue, SRT/VTT/TXT export, and prebuilt Docker Hub/GHCR images on NGC PyTorch 25.05.

Science & HPC

Beyond LLMs, GB10's unified memory and aarch64 stack run scientific compute: protein folding, biomolecular prediction, and RAN simulation.

  • adrian-greenneuron/openfold3-DGX-Spark - Dockerized OpenFold3 for DGX Spark with evoformer_attn kernels prebuilt, DeepSpeed patched from compute_121 to compute_120, ubiquitin prediction in 55 s.
  • chaoticcuriosity-io/g1-humanoid-rl - Unitree G1 humanoid RL on DGX Spark with mjlab, walking policy trained in about 46 min at 2048 envs and an 11 h cartwheel run at 4096 envs.
  • chaoticcuriosity-io/regolith - Synthetic-data lunar segmentation on DGX Spark with Isaac Sim 6.0 Replicator and SegFormer, where realistic ground cut real-photo rock over-prediction from 72.6% to 35.7%.
  • eetmie/spark-projects - Robotics playbooks for GB10 including openpi pi0.5 vision-language-action inference at 94.7 ms on TensorRT FP8 and NVFP4, 2.12x PyTorch BF16 at cosine 0.997.
  • rcbarke/ai-ran-dgx-spark - Bring-up notes for NVIDIA Aerial and Sionna on DGX Spark, with Sionna PHY and SYS working, cuMAC retargeted to run, and Sionna-RT and the 7.2x fronthaul blocked.
  • sanjyotshenoy/boltz-gb10-spark - Boltz-2 biomolecular-interaction prediction on DGX Spark with Triton-nightly sm_121 codegen.

Remote Access & Desktop

  • AtomicGaryBusey/DGXSparkGaming - Steam gaming compatibility log for DGX Spark under FEX-Emu, Box64, and Proton, with DLSS 4 frame generation working, DLSS 5 ruled out per frame, and every correction published.
  • seanGSISG/dgx-spark-sunshine-setup - One-command Sunshine installer for headless DGX Spark, NVIDIA CustomEDID virtual display with no dummy plug, 4K60 or 1440p120 within the GB10 pixel clock limit.

Tools & Monitoring

  • agjs/gb10-clock-cap - Clock-cap harness for GB10 inference hosts, where 2200 MHz ran 12 °C cooler at 36% less GPU-rail power for 1.0% decode and 3.9% prefill cost, single-stream at TP=2.
  • amer8/pulsebar - Unofficial macOS menu bar monitor that streams GPU and memory telemetry from the DGX Spark dashboard.
  • antheas/spark_hwmon - Linux hwmon kernel driver exposing GB10 system power telemetry (per-rail power, energy counters, temperatures) and PL1/PL2 power-cap controls via sysfs.
  • ateska/dgx-spark-prometheus - Single-binary Go Prometheus exporter with systemd unit and Grafana dashboard for DGX Spark, GB10 and NIC metrics on port 9835.
  • chappa-ai-llc/spark-smi - System-monitor TUI for DGX Spark with unified-memory and Grace P/E-core awareness, a cluster fleet view, an MT2910 fabric bandwidth test, and mixed sm_121 plus sm_86 support.
  • christopherowen/dgx-spark-fan-control - Kernel driver and CLI for RPM floors above NVIDIA's fan curve on DGX Spark, 13500 RPM floor measured at 9000 RPM in 6.3 s, with DKMS and Secure Boot signing.
  • DanTup/dgx_dashboard - Monitoring dashboard for DGX Spark bound to 0.0.0.0, with GB/GiB-correct memory stats, GPU power draw, and Docker container controls.
  • djmad/Spark_Energy_Management - Thermal and power controller for a ThinkStation PGX (GB10) with per-cluster CPU PID loops, a 100 MHz/s GPU clock ramp, and a thermal twin fitted to 1.2 K RMS.
  • dorangao/dgx-spark-toolkit - Two-node DGX Spark cluster scripts and manifests: RoCE and NCCL checks on the 200 Gb/s fabric, RDMA pods, MetalLB, pipeline-parallel vLLM Nemotron-3 Nano 30B.
  • drowzeys/vllm-gb10-spin-wait-fix - One-command patcher and English write-up for the vLLM spin-wait that heats GB10, 24 °C lower average SoC temperature on TP=2 multi-rank serves and no change at TP=1.
  • engineering87/sparkfit - Zero-dependency memory planner for DGX Spark: 128 GB budget split, quantization advisor, and decode roofline on 273 GB/s.
  • hectorTSH/dgx-spark-memory-dashboard - Live unified-memory occupancy map for DGX Spark as 1 GiB tiles, hot models against on-disk candidates ranked by free memory, and multi-Spark tabs.
  • hoesing/spark-gpu-throttle-check - Throttle test for DGX Spark that loads the GB10 with cuBLAS matmuls and flags clocks staying below a 1400 MHz threshold, a suspected USB-PD power-delivery fault.
  • ivanusto/gb10-ops - Host guards for GB10 that terminate the offending GPU process below 3 GiB MemAvailable and abort jobs after 240 s at 88 C, thresholds calibrated on one two-node box.
  • jasonacox/dgx-spark - Project hub for GB10 whose nanochat scripts pretrained a chat model from scratch in 9 days for about $8 of power, plus two-Spark InfiniBand training.
  • jeffrymahbuubi/dgx-spark-stress-test - Burn-in suite for GB10 unit qualification, 6-24 hour llama.cpp 70B plus SDXL load at ~96% utilization, ~85 GB resident, with 10s temperature and power CSVs.
  • jeremyeder/dgx-agentskills - Claude Code integration for DGX Spark: local model serving, GPU monitoring, and VM management.
  • joeynyc/spark-doctor - Read-only DGX Spark diagnostic CLI: 14 W power cap, unified-memory pressure, thermal risk, CUDA 13 / sm_121 wheel mismatches, Docker runtime, and recipe checks for tensor-parallel size and memory budget.
  • lcasarin-maker/blackbox - Forensic capture for GB10 hangs with Xid, PCIe AER, xHCI and PSI checks, plus a measured gap where 7 GiB held through PyTorch raised memory.current by 15 MiB.
  • lynx-lee/lynx-ollama - Ollama manager with a Go web console whose optimize command reads GB10 unified memory to set 131K context, 8-way parallel, and q8_0 KV cache.
  • mcampa/sparkrun-ui - Web UI for sparkrun with launch wizard, chat, benchmark charts, and live per-host GPU bars, run via npx or a published aarch64 container.
  • mchenetz/sparkd - Localhost dashboard for a DGX Spark fleet, with HF browsing, Claude-generated vLLM recipes, and single-box or Ray-cluster launch.
  • MiaAI-Lab/sparkDash - Web dashboard for a DGX Spark fleet with an engine probe for llama.cpp, vLLM, SGLang, ds4, and EXL3, cached against uncached prefill, daily peak tok/s, and Wake-on-LAN.
  • parallelArchitect/sparkview - Terminal GPU monitor with GB10-aware unified-memory reporting, memory-pressure (PSI) and power-rail readouts, and an anomaly auto-logger.
  • r0b0tlab/hermes-concurrent-agents - Supervised Hermes Agent worker pool for one Linux host, with pre-claim admission, exact process ownership, and optional GB10 memory-pressure presets.
  • securitysonar/spark-hashcat - Hashcat REST API service for GB10 aarch64, with an NVRTC CUDA build path that bypasses OpenCL.
  • skymaze/Fireworks - Web control plane for a DGX Spark fleet, ARP-probed RoCE rail configuration with rollback, and model direct-pull to workers over the four rails.
  • stevibe/SparklingKit - Local-first workspace for OCR, transcription, grounding, and image jobs, routed to six co-resident models on one DGX Spark from Qwen3.6-35B-A3B NVFP4 to LocateAnything-3B.
  • TheAwaken1/Spark-Studio - Launch and tuning dashboard for vLLM, SGLang, llama.cpp, and sparkrun recipes on DGX Spark that hands a broken recipe to Claude Code or Codex to patch and relaunch.
  • vybe/sparky - Vue 3 web UI for DGX Spark with Ollama chat, a Claude Code agent tab, ComfyUI SDXL and Flux generation, and Docker/systemd control.
  • wentbackward/nv-monitor - Terminal monitor and Prometheus exporter for DGX Spark in one zero-dependency C binary, with HugePages-correct unified memory and Grace big.LITTLE core labels.
  • Z841973620/dgx-spark-fan-override - Kernel module overriding DGX Spark fan speed through the EC's FF-A eSPI mailbox, with the stock firmware's two temperature curves and 1,260-13,500 RPM ranges documented.

Operating Systems & Containers

  • graham33/nixos-dgx-spark - Nix flake with a NixOS module for NVIDIA's DGX Spark kernel, bootable USB image, and 15 playbook devshells for TRT-LLM, NVFP4, and NCCL over QSFP.
  • kindlingai/kindling-spark-os - Read-only OS image for GB10 booted beside DGX OS with auto-revert and a 2 GiB display carveout lent to CUDA, GLM-5.3 TP=4 KV pool 365,440 to 404,608 tokens.
  • kyuz0/gb10-toolboxes - Prebuilt aarch64 CUDA 13.x containers for GB10 sm_121 with llama.cpp, antirez/ds4 and vLLM, rebuilt on four-hour upstream polls.
  • maxspevack/spark-rocky - Rocky Linux 10.2 Live-USB for DGX Spark on the CIQ 6.18 kernel, shipping 4k pages because 64k faults on every driver branch but the 580, measured 10.4% slower.
  • Neural-ICE/ICE-CoreOS - Immutable bootc OS for DGX Spark on CentOS Stream 10 with a 4 KiB-page GB10 kernel, optional TPM2-unlocked LUKS2, and a signed-UKI USB installer.
  • RageLtd/arch-dgx-spark-iso - Arch Linux installer ISO builder for DGX Spark, with the linux-dgx-spark kernel and archinstall config.

Community & Resource Collections

  • AEON-7/AEON-7 - Index of AEON-7's releases, mainly DGX Spark NVFP4 model packs, prebuilt vLLM images, and a voice-AI stack, plus Apple Silicon MLX builds.
  • odnodn/dgx-spark - Curated collection of NVIDIA DGX Spark resources and self-hosted AI projects.

Contributing

Contributions are welcome. Read the contribution guidelines before opening a pull request.

About

A curated list of tools, guides, playbooks, and resources for the NVIDIA DGX Spark (GB10 Grace Blackwell personal AI supercomputer).

Topics

awesomeawesome-listblackwelldgx-sparkgb10llmnvidia

Resources

Readme
CC0-1.0 license

Contributing

Contributing
Activity

Stars

76 stars

Watchers

0 watching

Forks

7 forks
Report repository

Releases

Packages

Contributors

Languages