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

2 best points · 2 comments · 1 Hacker News post · 160 GitHub stars · View on GitHub

Hacker News discussions

• Native Rust/C++ LLM inference engine (2 points, 2 comments, by nylanderjens, 2026-09-04)