Private chat and code on your Mac. Run a 177B model on a 128 GB M5 Max: local Qwen3.8 Flash-Next inference with a 65,536-token default or optional 131,072-token context, Tokspur's own Metal engine with native MTP or DFlash2 drafting, and an OpenAI-compatible API. Apache 2.0.
The fastest way to run Qwen 3.8 Flash Next, Qwen 3.8 27B and Ternary Bonsai 2 27B on a Mac: 125 tok/s in OpenCode on an M5 Max, and a 27B model on 16 GB Macs. Native MTP speculative decoding on Apple Silicon, exact at any temperature. OpenAI and Anthropic compatible local server.
Fork of antirez/ds4 for Apple Silicon, tuned mostly for M1/M2: Qwen3.8-Flash-Next with 262K context on 64 GB and up, 35 tok/s on an M1 Max, MTP and vision, one-line install.
The local AI app built for the Mac. Run LLMs like Qwen, Gemma and GPT-OSS on Apple Silicon, including models far bigger than your Mac's memory, by streaming MoE experts from the SSD.
macMLX brings local LLM inference to Apple Silicon with a first-class native macOS experience. No cloud, no telemetry, no Electron — just your Mac running models at full speed.