GitHub intelligence
youssofal/
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.
Observed OCT 8, 2026 · 00:08 UTC
Facts
- Language
- Python
- License
- apache-2.0
- Created
- MAY 2, 2026
- Last push
- Last release
- Website
- mtplx.com ↗
- GitHub
- youssofal/MTPLX ↗
Measurements
- Stars
- 2,500
- Forks
- 197
- 7D change
- Collectingfrom OCT 9
- 30D change
- Collectingfrom NOV 1
- 90D change
- Collectingfrom DEC 31
- Velocity
- Collectingfrom OCT 16
- Acceleration
- Collectingfrom OCT 23
- Trajectory
- Collectingfrom OCT 16
- Trending percentile
- Collectingfrom OCT 16
Categories
Technologies
Star history
Daily history began OCT 2. The chart appears after 7 days. 1 observed day shown.
Observed days (1)
| Day | Stars | Forks |
|---|---|---|
| OCT 2 | 2,500 | 197 |