Add native Qwen3.8 27B model lanes

CHANGELOG.md

@@ -28,6 +28,27 @@ The format is based on Keep a Changelog.
 
 ### Runtime
 
+- added `vision-chat-q38-27b`, pinned to Qwen's official Apache-2.0
+  Qwen3.8-27B BF16 checkpoint. The native Qwen-family runtime now exposes the
+  dense 27B hybrid-attention model's text, code, and image understanding,
+  published 262,144-token context, thinking and sampling defaults, complete
+  generation EOS set, and Qwen3.8 image sizing. The 55.59 GB pull is explicit
+  rather than an inference-time auto-download and is gated to 64 GB unified
+  memory with 96 GB recommended. The coding benchmark accepts Qwen3.8 as an
+  explicit model and scores only visible code after separating reasoning. The
+  runtime can load the checkpoint's embedded dense MTP head for opt-in
+  three-token greedy drafts. It remains experimental because BF16 multi-token
+  verification can diverge from serial greedy decode; the default, sampled,
+  and constrained requests retain the target-only path.
+- added the separate `vision-chat-q38-27b-4bit` managed lane, pinned to LM
+  Studio's 4-bit/group-64 MLX conversion. Its 19.47 GB composite pull mounts
+  only Qwen's pinned final BF16 shard under `mtp/`, retaining the official MTP
+  head and license without duplicating the 55.59 GB checkpoint. Target-only
+  decode remains the default; `MERERUN_Q35_MTP_SPECULATION=1` enables the
+  explicitly experimental fast path. A deterministic 24-task stride through
+  the official HumanEval set scored 20/24 in both modes with the same failures;
+  one failing case changed length by three tokens, so MTP remains opt-in rather
+  than claiming exact greedy-output parity.
 - refreshed the owned MLX and mlx-swift forks onto current upstream cutoffs,
   retained the scoped 1-bit, NVFP4, CUDA, stream-safety, and M4/H3 patches,
   made the generated NAX optimizations source-reproducible, and regenerated

README.md

@@ -53,7 +53,7 @@ current flags.
 | Area | Public commands | Current surface |
 | --- | --- | --- |
 | Images and LoRAs | `image generate`, `image train-lora`, `adapter list`, `adapter pull` | Klein, ZImage, HiDream O1, Krea 2, Ideogram 4, and Bonsai; text-to-image, edits, multiple references, structured prompts, local Krea/Klein training, and checksum-pinned public adapters |
-| Text, code, and agents | `text chat`, `text code`, `text embed`, `text anonymize`, `text train-lora`, `agent` | Local chat and tool use, including Bonsai 27B binary/ternary vision chat; code generation, embeddings, PII redaction, text LoRA training, and guided local-agent setup |
+| Text, code, and agents | `text chat`, `text code`, `text embed`, `text anonymize`, `text train-lora`, `agent` | Local chat and tool use, including Qwen3.8 27B BF16/4-bit and Bonsai 27B binary/ternary vision chat; code generation, embeddings, PII redaction, text LoRA training, and guided local-agent setup |
 | Vision understanding | `vision caption`, `inspect`, `face`, `ground`, `segment`, `track`, `track-live`, `pose`, `flow`, `ocr` | Captioning and VQA, local face detection/identity embeddings, LightOn/GLM/Infinity OCR, Falcon grounding, SAM 3.1 segmentation and tracking, body/hand/face landmarks, and dense optical flow |
 | Depth, geometry, and 3D | `vision depth-video`, `geometry`, `geometry-multiview`, `image-to-3d*`; `image reconstruct-3d*` | Video Depth Anything, MoGe-2, Depth Anything 3, TripoSR, InstantMesh, and TRELLIS.2; depth/confidence EXRs, cameras, point clouds, 3DGS initialization, OBJ, PLY, GLB, and PBR voxel artifacts |
 | Audio enhancement | `audio enhance` | Native AP-BWE speech bandwidth extension and UniverSR general-audio super-resolution to hashed 48 kHz mono WAVs |

Sources/MereRunCLI/Commands/ModelBenchmarkCodeCommand.swift

@@ -257,7 +257,7 @@ struct ModelBenchmarkCode: AsyncParsableCommand {
         guard let spec = ManagedModelCatalog.spec(for: modelID) else {
             return CodeBenchmarkModelResult.missing(model: modelID, reason: "Unknown model id.")
         }
-        guard spec.category == .textCode else {
+        guard Self.supportsCodingBenchmark(spec) else {
             return CodeBenchmarkModelResult.missing(model: modelID, reason: "Model is not a text-code model.")
         }
         guard let installedURL = ManagedModelResolver.resolveInstalledModel(id: modelID) else {
@@ -344,7 +344,7 @@ struct ModelBenchmarkCode: AsyncParsableCommand {
             do {
                 let response = try await generate(request)
                 let generationSeconds = Date().timeIntervalSince(generationStart)
-                let candidate = task.candidateProgram(from: response.response)
+                let candidate = task.candidateProgram(from: Self.scoredCodeResponse(response))
                 let execution = try CodeExecutionSandbox.runPython(
                     program: task.testProgram(candidateProgram: candidate),
                     python: python,
@@ -422,6 +422,15 @@ struct ModelBenchmarkCode: AsyncParsableCommand {
             || ManagedModelCatalog.spec(for: modelID)?.validationKind == .q35
     }
 
+    static func supportsCodingBenchmark(_ spec: ManagedModelSpec) -> Bool {
+        spec.category == .textCode
+            || Q35Resources.isQ38ModelId(spec.id)
+    }
+
+    static func scoredCodeResponse(_ response: ChatResponse) -> String {
+        ChatReasoningMarkup.splitThinkBlocks(in: response.response).visibleContent
+    }
+
     static let systemPrompt = """
     You are completing Python programming benchmark tasks. Return only valid Python code.
     Do not include Markdown fences, prose, comments about your approach, or test code.

Sources/MereRunCore/ManagedModelCatalog.swift

@@ -1652,6 +1652,56 @@ public enum ManagedModelCatalog {
             defaultCLICommands: ["chat", "api serve"],
             apiProfile: .q36(contextWindow: Q35Resources.defaultContextLength)
         ),
+        ManagedModelSpec(
+            id: Q35Resources.q38TwentySevenBModelId,
+            category: .visionChat,
+            installShape: .directoryRoot,
+            hubFallback: Q35Resources.profile(for: Q35Resources.q38TwentySevenBModelId)?.hubFallbackConfig,
+            upstreamRepoId: Q35Resources.q38TwentySevenBUpstreamRepoId,
+            upstreamRevision: Q35Resources.q38TwentySevenBUpstreamRevision,
+            validationKind: .q35,
+            runtimeAutoDownloadAllowed: false,
+            estimatedDownloadBytes: Q35Resources.q38TwentySevenBEstimatedDownloadBytes,
+            defaultCLICommands: [
+                "text chat",
+                "api serve",
+                "model benchmark chat",
+                "model benchmark code",
+                "model benchmark vlm",
+            ],
+            apiProfile: .q36(contextWindow: Q35Resources.q38TwentySevenBContextLength)
+        ),
+        ManagedModelSpec(
+            id: Q35Resources.q38TwentySevenB4BitModelId,
+            category: .visionChat,
+            installShape: .directoryRoot,
+            hubFallback: Q35Resources.profile(
+                for: Q35Resources.q38TwentySevenB4BitModelId
+            )?.hubFallbackConfig,
+            mountedHubFallbacks: [
+                MountedHubFallbackConfig(
+                    destinationPath: Q35Resources.q38MTPComponentPath,
+                    hubFallback: HubFallbackConfig(
+                        repoId: Q35Resources.q38TwentySevenBUpstreamRepoId,
+                        revision: Q35Resources.q38TwentySevenBUpstreamRevision,
+                        patterns: Q35Resources.q38MTPComponentSnapshotPatterns
+                    )
+                ),
+            ],
+            upstreamRepoId: Q35Resources.q38TwentySevenB4BitUpstreamRepoId,
+            upstreamRevision: Q35Resources.q38TwentySevenB4BitUpstreamRevision,
+            validationKind: .q35,
+            runtimeAutoDownloadAllowed: false,
+            estimatedDownloadBytes: Q35Resources.q38TwentySevenB4BitEstimatedDownloadBytes,
+            defaultCLICommands: [
+                "text chat",
+                "api serve",
+                "model benchmark chat",
+                "model benchmark code",
+                "model benchmark vlm",
+            ],
+            apiProfile: .q36(contextWindow: Q35Resources.q38TwentySevenBContextLength)
+        ),
         ManagedModelSpec(
             id: Q35Resources.bonsai27B1BitModelId,
             category: .textChat,
@@ -3513,7 +3563,12 @@ public extension ManagedModelSpec {
         case .lagunaDFlash:
             return LagunaResources.missingDFlashFiles(rootURL: rootURL, fileManager: fileManager)
         case .q35:
-            return Q35Resources(rootURL: rootURL).validate(fileManager: fileManager)
+            let resources = Q35Resources(rootURL: rootURL)
+            var missing = resources.validate(fileManager: fileManager)
+            if id == Q35Resources.q38TwentySevenB4BitModelId {
+                missing.append(contentsOf: resources.validateQ38MTPComponent(fileManager: fileManager))
+            }
+            return missing
         case .lfm2:
             return LFM2Resources(rootURL: rootURL).validate(
                 fileManager: fileManager,

Sources/MereRunCore/ManagedModelSupport.swift

@@ -409,6 +409,20 @@ public enum ManagedModelCapabilityCatalog {
                 recommended: 32,
                 setup: true
             ),
+            descriptor(
+                Q35Resources.q38TwentySevenBModelId,
+                "Qwen3.8 27B vision chat",
+                "Runs Qwen's official dense 27B BF16 vision-language checkpoint through the native Qwen-family runtime.",
+                minimum: 64,
+                recommended: 96
+            ),
+            descriptor(
+                Q35Resources.q38TwentySevenB4BitModelId,
+                "Qwen3.8 27B 4-bit vision chat",
+                "Runs LM Studio's pinned MLX 4-bit conversion with Qwen's official MTP shard available for explicit speculative decode.",
+                minimum: 32,
+                recommended: 48
+            ),
             descriptor(
                 Q35Resources.bonsai27B1BitModelId,
                 "Bonsai 27B 1-bit vision chat",

Sources/MereRunCore/MereRunModelManifest.swift

@@ -30,7 +30,7 @@ public struct MereRunModelManifest: Codable, Hashable, Sendable {
         case lfm2 = "lfm2"
         /// Poolside Laguna family via the native Swift runtime.
         case laguna = "laguna"
-        /// Q35 family (Qwen3.5 hybrid MoE + hybrid attention).
+        /// Qwen3.5-family dense or MoE models with hybrid attention.
         case qwen35HybridMoE = "qwen3.5-hybrid-moe"
         /// SAM image segmentation family.
         case samSegmentation = "sam-segmentation"
@@ -1086,6 +1086,37 @@ public struct MereRunModelManifest: Codable, Hashable, Sendable {
                 upstreamRepoId: "\(Q35Resources.q36NanoUpstreamRepoId)@\(Q35Resources.q36NanoUpstreamRevision)",
                 createdAt: createdAt
             )
+        case .q38TwentySevenB:
+            return MereRunModelManifest(
+                id: modelID.rawValue,
+                engine: .qwen35HybridMoE,
+                family: .qwen,
+                tier: .latest,
+                variant: .standard,
+                precision: .bf16,
+                defaults: nil,
+                supports: [.chat, .codeGeneration, .visionChat],
+                components: q35TextComponents,
+                upstreamRepoId: "\(Q35Resources.q38TwentySevenBUpstreamRepoId)"
+                    + "@\(Q35Resources.q38TwentySevenBUpstreamRevision)",
+                createdAt: createdAt
+            )
+        case .q38TwentySevenB4Bit:
+            return MereRunModelManifest(
+                id: modelID.rawValue,
+                engine: .qwen35HybridMoE,
+                family: .qwen,
+                tier: .latest,
+                variant: .standard,
+                precision: .int4,
+                quantization: Quantization(bits: 4, groupSize: 64, scheme: "mlx-affine"),
+                defaults: nil,
+                supports: [.chat, .codeGeneration, .visionChat],
+                components: q35TextComponents,
+                upstreamRepoId: "\(Q35Resources.q38TwentySevenB4BitUpstreamRepoId)"
+                    + "@\(Q35Resources.q38TwentySevenB4BitUpstreamRevision)",
+                createdAt: createdAt
+            )
         case .bonsai27B1Bit:
             return MereRunModelManifest(
                 id: modelID.rawValue,

Sources/MereRunCore/MereRunModelValidator.swift

@@ -648,7 +648,9 @@ public enum MereRunModelValidator {
             return .liquid
         }
         if modelId == ModelResolver.ModelID.q36Nano.rawValue
-            || modelId == ModelResolver.ModelID.q36NanoGGUF.rawValue {
+            || modelId == ModelResolver.ModelID.q36NanoGGUF.rawValue
+            || modelId == ModelResolver.ModelID.q38TwentySevenB.rawValue
+            || modelId == ModelResolver.ModelID.q38TwentySevenB4Bit.rawValue {
             return .qwen
         }
         return nil

Sources/MereRunCore/ModelResolver.swift

@@ -44,6 +44,8 @@ public struct ModelResolver {
         case nemotron35LightningDSpark = "text-chat-nemotron-35-lightning-dspark"
         case ltxGemma3TwelveB4Bit = "text-encoder-ltx-gemma3-12b-4bit"
         case q36Nano = "text-chat-q36-nano"
+        case q38TwentySevenB = "vision-chat-q38-27b"
+        case q38TwentySevenB4Bit = "vision-chat-q38-27b-4bit"
         case bonsai27B1Bit = "text-chat-bonsai-27b-1bit"
         case bonsai27B2Bit = "text-chat-bonsai-27b-2bit"
         case lfm25A1B8Bit = "text-chat-lfm25-a1b-8bit"

Sources/MereRunCore/Q35/Q35Config.swift

@@ -1,5 +1,27 @@
 import Foundation
 
+public struct Q35GenerationConfig: Codable, Sendable, Hashable {
+    public let eosTokenIds: [Int]
+
+    private enum CodingKeys: String, CodingKey {
+        case eosTokenId = "eos_token_id"
+    }
+
+    public init(from decoder: Decoder) throws {
+        let container = try decoder.container(keyedBy: CodingKeys.self)
+        if let single = try? container.decode(Int.self, forKey: .eosTokenId) {
+            eosTokenIds = [single]
+        } else {
+            eosTokenIds = try container.decodeIfPresent([Int].self, forKey: .eosTokenId) ?? []
+        }
+    }
+
+    public func encode(to encoder: Encoder) throws {
+        var container = encoder.container(keyedBy: CodingKeys.self)
+        try container.encode(eosTokenIds, forKey: .eosTokenId)
+    }
+}
+
 public struct Q35QuantizationConfig: Codable, Sendable, Hashable {
     public let groupSize: Int
     public let bits: Int