Mtplx
starred
Application
3x faster speeds on MLX | Qwen 3.8 27B | Native MTP Speculative Decoding On Apple Silicon With No External Drafter.
Filament plugins, Laravel packages and open source starter kits actively maintained. All MIT, with releases for v3, v4 and v5 where applicable.
3x faster speeds on MLX | Qwen 3.8 27B | Native MTP Speculative Decoding On Apple Silicon With No External Drafter.
Model-neutral agent desktop/runtime for private, enterprise, and OpenAI-compatible / Anthropic-compatible model API. Tested on DeepSeek, Qwen, Kimi, GLM models. Supports MCP, Skills,and local code search.
All packages have CI, Pest tests and open issues tagged good first issue.
New version available.