feat(AI): MNN 文本模型升到 Qwen3.5-4B(taobao-mnn 预转换)

现场机 iPhone 17(A19/SME2)内存与加速均可承载 4B,质量优于 2B。

- ModelKind.mnnLLM rawValue → "Qwen3.5-4B-MNN",displayName → Qwen3.5-4B (MNN/SME2)
- ModelManifest:7 个运行时文件(llm.mnn.weight ~2.45GB + 拆分的
  visual.mnn.weight 188MB),总计 2,836,770,850 bytes(~2.64GiB)
- ModelManifestTests:文件数 7 / 总字节 / URL 更新到 Qwen3.5-4B-MNN
- CLAUDE.md §2:MNN 主模型记为 Qwen3.5-4B,MLX 兜底仍 2B

模拟器 ModelManifestTests TEST SUCCEEDED。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
link2026
2026-06-08 20:28:14 +08:00
parent 39b1521f00
commit cbacd9461a
4 changed files with 15 additions and 14 deletions

View File

@@ -60,17 +60,18 @@ nonisolated enum ModelManifest {
ModelFile(path: "video_preprocessor_config.json", bytes: 817),
]
case .mnnLLM:
// taobao-mnn/Qwen3.5-2B-MNN MNN (HF API ,2026-06)
// taobao-mnn/Qwen3.5-4B-MNN MNN (HF API ,2026-06)
// :config.json(MNN llm )+ llm_config.json()+ llm.mnn()
// + llm.mnn.weight( ~1.1GB)+ tokenizer.txt + visual.mnn(, mllm)
// README/.gitattributes dump(llm.mnn.json / export_args.json)
// + llm.mnn.weight( ~2.45GB)+ tokenizer.txt + visual.mnn/visual.mnn.weight(,
// mllm,) README/.gitattributes dump
return [
ModelFile(path: "config.json", bytes: 652),
ModelFile(path: "llm_config.json", bytes: 8_692),
ModelFile(path: "llm.mnn", bytes: 2_148_136),
ModelFile(path: "llm.mnn.weight", bytes: 1_176_647_702),
ModelFile(path: "llm_config.json", bytes: 8_693),
ModelFile(path: "llm.mnn", bytes: 3_651_096),
ModelFile(path: "llm.mnn.weight", bytes: 2_629_387_626),
ModelFile(path: "tokenizer.txt", bytes: 6_465_727),
ModelFile(path: "visual.mnn", bytes: 488_096),
ModelFile(path: "visual.mnn.weight", bytes: 196_768_960),
]
}
}