GitHub · Rust
Pushkinist/rMLX
Native Rust, single-binary MLX inference server for Apple Silicon. OpenAI/Anthropic-compatible LLM serving — text, vision, audio, embeddings — with the widest weight×KV quantization matrix of any MLX server. No Python, no GGUF.
- Stars
- 18
- Forks
- 7
- Stars gained in 24 hours
- 0
- Forks gained in 24 hours
- 0
Topics: apple-silicon, kv-cache, llm, metal, mlx, quantization, rust, turboquant, anthropic, claude-code
Latest data point: Nov 21, 2026 · 18 stars · 7 forks