mtplx

3x faster speeds on MLX | Qwen 3.8 27B | Native MTP Speculative Decoding On Apple Silicon With No External Drafter.

Spin up your agent loop. One CLI to run a fleet of LLMs on local machine / LAN / Tailscale or on GPU instances in AWS.

Run local MLX models with Pi — zero config, automatic model discovery, and live token-speed monitoring.

Run an isolated Claude Science app copy through local or OpenAI-compatible model backends.

Beautiful, zero-dependency realtime dashboard + live activity log for a local MTPLX inference server — reads the /metrics endpoint, no build step.

Native macOS menu-bar controller for local MTPLX model daemons.

Recover the native MTP predictor missing from the 8-bit MLX Qwen3.8-27B-Uncensored package, build a BF16 sidecar, and reproduce a 15.59 → 48.75 tok/s controlled M4 Max result with MTPLX.

Double Qwen 3.8 27B inference speed on Apple Silicon with a one-click local coding agent