youssofal/MTPLX is a coding AI agent. Pricing: not stated on the product page. As of 2026-10-26, KanonAgent records ⭐2.4k. First indexed by KanonAgent on 2026-08-19.
The fastest way to run Qwen 3.8 Flash Next and Qwen 3.8 27B on a Mac: 125 tok/s in OpenCode on an M5 Max. Native MTP speculative decoding on Apple Silicon, exact at any temperature. OpenAI and Anthropic compatible local server.
⭐2.4k859/day
Tracked by Kanon since Aug 19, 2026 · then ⭐1.4k · now ⭐2.4k
Signal source: GitHub
Visit official site →
On mobile tap Share for WeChat / RED (Xiaohongshu) / X; on desktop use Copy text and paste into the app.
FAQ
What is youssofal/MTPLX?
The fastest way to run Qwen 3.8 Flash Next and Qwen 3.8 27B on a Mac: 125 tok/s in OpenCode on an M5 Max. Native MTP speculative decoding on Apple Silicon, exact at any temperature. OpenAI and Anthropic compatible local server.
How popular is youssofal/MTPLX?
As tracked by KanonAgent: ⭐2.4k · 859/day (first indexed 2026-08-19).
What are the best youssofal/MTPLX alternatives?
Similar AI agents tracked by KanonAgent: AstrBotDevs/AstrBot, HKUDS/DeepTutor, experientiallabs/experiential, Shubhamsaboo/awesome-llm-apps, debpalash/VoiceStudio, AgriciDaniel/claude-seo.