Qwen3 Rs — Development skill for Claude Code
A Qwen3.5 inference engine built by a group of agents on Slock.
How to install Qwen3 Rs
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open wangrunji0408/qwen3-rs and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Qwen3 Rs does
A Qwen3.5 inference engine built by a group of agents on Slock.
Alternatives in Development
- IPolloWork — Enterprise-grade, local-first Agent Workbench for people and agent teams 4.9k ★
- Magnitude — Open source inference server your agent sets up for you 1.5k ★
- Haft — Engineering decisions engine that know when they're stale 1.4k ★
README
qwen3-rs
Qwen3.5 推理引擎,纯 Rust 实现,针对 Apple Silicon (M1) 优化。
本项目由一群 [Claude Sonnet](https://www.anthropic.com/claude) Agent 在 [Slock](https://slock.ai) 平台上协作完成。

性能(M1 Pro)
| 模型 | Prefill | Decode |
|---|---|---|
| Qwen3.5-0.8B | ~234 tok/s | ~21 tok/s |
| Qwen3.5-9B | ~52 tok/s | ~2.4 tok/s |
| Ollama 基准 (qwen3.5:0.8b-bf16) | 231 tok/s | 35 tok/s |
前置条件
- macOS(Apple Silicon M1)
- Rust 1.85+
- Qwen3.5 模型文件(safetensors 格式)
下载模型
# 0.8B 模型
huggingface-cli download Qwen/Qwen3.5-0.8B \
--local-dir ~/Models/Qwen3.5-0.8B \
--include "*.json" "*.safetensors" "tokenizer*"
# 9B 模型
huggingface-cli download Qwen/Qwen3.5-9B \
--local-dir ~/Models/Qwen3.5-9B \
--include "*.json" "*.safetensors" "tokenizer*"
编译
cargo build --release
使用
交互式对话
./target/release/qwen3-rs chat \
--model ~/Models/Qwen3.5-0.8B \
--max-tokens 512 \
--temperature 0.7 \
--thinking
文本生成
./target/release/qwen3-rs generate \
--model ~/Models/Qwen3.5-0.8B \
--prompt "What is 2+2?" \
--max-tokens 50
性能测试
./target/release/qwen3-rs benchmark \
--model ~/Models/Qwen3.5-0.8B \
--prefill-len 64 \
--decode-len 50
正确性验证
./target/release/qwen3-rs verify --model ~/Models/Qwen3.5-0.8B
运行测试
QWEN_MODEL_DIR=~/Models/Qwen3.5-0.8B cargo test
项目结构
src/
├── main.rs # CLI 入口(generate / benchmark / verify / chat)
├── config.rs # 模型配置
├── loader.rs # safetensors 权重加载(mmap 零拷贝)
├── tokenizer.rs # 分词器封装
├── inference.rs # 推理主循环(prefill + decode)
├── sampling.rs # 采样(greedy / temperature)
├── model/
│ ├── text.rs # 完整 Transformer 模型
│ ├── attention.rs # 全注意力层(GQA + MRoPE)
│ ├── gated_delta_net.rs # GatedDeltaNet 线性注意力层
│ ├── cache.rs # KV cache
│ ├── rope.rs # RoPE 旋转位置编码
│ └── vision.rs # 视觉编码
└── ops/
├── blas.rs # BLAS(Accelerate + NEON BF16 G
Related Skills
Launch Google Search
Launch a complete Google Ads Search campaign — campaign, ad group, responsive search ads, keywords, sitelinks,
Launch Pmax
Launch a Google Ads Performance Max campaign with a complete asset group, audience signals, and (for ecom) lis
Tidewright
A 3D sandcastle simulator that runs entirely on the GPU. No engine, no libraries, no asset files, no build ste
Pygin
Pygin - a from-scratch UCI chess engine in Python + C, with a hand-written search and evaluation and the entir
Navin Engine
Rust-native MCP engine that breaks, diagnoses, repairs, benchmarks, and certifies software changes before they
Gvs5h
GVS5H: Five Qwen3.8-27B Models Match Claude Fable 5 on LiveCodeBench Hard Fable 5 Level Coding for a Fifth the
Related Agents
Reasoning Engine
Use this agent for systematic logical inference and structured problem-solving. Specializes in multiple reason
Funnel Diagnostician
Diagnostic inference engine that reads all data sources, builds AARRR funnel model, scores each stage, identif
Wp Cinematic
Cinematic scroll-driven theme specialist. Reads cinematic-scroll-kit's schemas/scene.json contract and generat