🔥 The fastest local AI engine for Apple Silicon. Optimised for agentic use.
Like samuelfaj/lightning-mlx, 0 likes 0 Bookmark samuelfaj/lightning-mlx, 0 bookmarks 0 mac code — Claude Code, but it runs on your Mac for free. 35B AI agent at 30 tok/s via Apple Silicon flash-paging. $0/month.
Like walter-grace/mac-code, 0 likes 0 Bookmark walter-grace/mac-code, 0 bookmarks 0 A local inference engine for Apple silicon, built around the model.
Like incoai/splash, 0 likes 0 Bookmark incoai/splash, 0 bookmarks 0 The 80B Qwen3-Coder-Next on a 16 GB Mac, about 13 tok/s, fully offline. A mixture-of-experts inference engine for Apple silicon.
Like 1picassoai/coachwhip, 0 likes 0 Bookmark 1picassoai/coachwhip, 0 bookmarks 0 Local AI, native to your Mac. Chat, serve, monitor, and connect MLX models from one macOS app.
Like Blaizzy/nativ, 0 likes 0 Bookmark Blaizzy/nativ, 0 bookmarks 0 MLX Studio - Easiest way to run LLM's on your Mac. All in one engine.
Like jjang-ai/mlxstudio, 0 likes 0 Bookmark jjang-ai/mlxstudio, 0 bookmarks 0 works well with rocks; native Apple Silicon inference engine for capable and tiny models (ternary, Qwen) via MLX Swift. Hadamard-rotated KV cache, vision, tool calling, OpenAI + Anthropic APIs
Like struffl/ishizuki, 0 likes 0 Bookmark struffl/ishizuki, 0 bookmarks 0 Fastest LLM inference runtime for Apple Silicon
Like basecompute/baseRT, 0 likes 0 Bookmark basecompute/baseRT, 0 bookmarks 0 LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar
Like jundot/omlx, 1 like 1 Bookmark jundot/omlx, 0 bookmarks 0