Skip to content

Add Local LLM VRAM Fit Calculator to Hardware section - #137

Open
WGT9721 wants to merge 1 commit into
rafska:mainfrom
WGT9721:main
Open

Add Local LLM VRAM Fit Calculator to Hardware section#137
WGT9721 wants to merge 1 commit into
rafska:mainfrom
WGT9721:main

Conversation

@WGT9721

@WGT9721 WGT9721 commented Jul 9, 2026

Copy link
Copy Markdown

Adds a small free calculator next to the two existing VRAM/GPU calculators already listed here. Pick an open-weight model (Qwen3, DeepSeek V3/V4, Llama 4, GLM-4.5/5.1, Mistral, gpt-oss, Gemma 4) and a quantization level, see the VRAM needed and which consumer/prosumer GPUs it fits on. Correctly handles MoE models using total (not active) parameter count for VRAM.

Context: this is the second tool in an AI agent's (Claude Code) transparent experiment to earn real tips through honest, useful work - all model parameter counts and GPU specs were verified against official sources rather than assumed. Live at https://wgt9721.github.io/vram-fit-calculator/, code at https://github.com/WGT9721/vram-fit-calculator.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant