MTPLX
by youssofal (personal account)
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. (description from the project’s GitHub page)
Repository facts
- Stars
- 2,598
- Forks
- 202
- Open issues and pull requests
- 79
- Primary language
- Python
- License
- Apache License 2.0 (Apache-2.0)
- Owner
- youssofal · Personal account
- Created
- May 2, 2026
- Last push
- Oct 10, 2026
Topics
Add this badge to your README
Shows this repository’s rank in AI on GitHub and links back to this page. Ranks are by stars and change when the list is refreshed. The badge is not an endorsement or a rating. About the badges
Markdown (for a README)
[](https://unitedstatesofamericasuperintelligence.com/github/youssofal--mtplx/)
HTML
<a href="https://unitedstatesofamericasuperintelligence.com/github/youssofal--mtplx/"><img src="https://unitedstatesofamericasuperintelligence.com/badges/github/youssofal--mtplx.svg" alt="Ranked #2,959 in AI on GitHub" height="20"></a>
Related projects
Projects that share this one’s GitHub topics.
Rank 7,596: ARahim3/mlx-dspark
Up to 4× faster LLM decoding on Apple Silicon, lossless. Native MLX port of DeepSeek's DSpark & z-lab's DFlash speculative decoding — Gemma-4, Qwen3.8, Muse-Glimmer, Nemotron, LFM…
719 starsPythonMITLast push Oct 5, 2026
Rank 1,979: raullenchai/Rapid-MLX
Rapid-MLX is an open-source (Apache 2.0) OpenAI- and Anthropic-compatible LLM inference server for Apple Silicon, built on MLX, focused on reliable tool calling for coding agents.…
3,996 starsPythonOther licenseLast push Oct 18, 2026
Rank 5,991: StayLameBro/backburner
Your iPhone helps your Mac run a 27B model: faster prompt reading and more context over a USB-C cable
1,033 starsPythonMITLast push Oct 13, 2026
Rank 2,336: nicedreamzapp/claude-code-local
Run Claude Code 100% on-device with local AI on Apple Silicon. MLX-native Anthropic-API server. 6 fighters incl. Muse-Glimmer 30B (now multimodal — reads images, abliterated), Gem…
3,369 starsPythonMITLast push Oct 15, 2026
Rank 4,327: waybarrios/vllm-mlx
High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuous batching, multimodal models, MCP tool calling, and Claude Code supp…
1,626 starsPythonApache-2.0Last push Oct 16, 2026
Rank 3,960: AtomicBot-ai/Atomic-Chat
Local AI app and inference engine for agents. Run open-weight LLMs locally — private, 100% offline on your computer. Join our Discord: https://discord.com/invite/8wGSsvmg4V
1,810 starsTypeScriptOther licenseLast push Oct 17, 2026