GitHub · Rust
truespar/paddock
Native Rust inference server for open models on NVIDIA and Apple Silicon. OpenAI- and Anthropic-compatible APIs, GGUF + safetensors + MLX, FP8/NVFP4/MXFP4/Q8/Q4, built-in Studio
- Stars
- 164
- Forks
- 25
- Stars gained in 24 hours
- 0
- Forks gained in 24 hours
- 0
Topics: ai, aimodels, blackwell, cuda, inference, inference-engine, inference-optimization, macos, metal, mlx
Latest data point: Nov 21, 2026 · 164 stars · 25 forks