flash-next

Open repos and models their makers tagged flash-next, most starred first. The same for everyone.

AI on my own machineRepo

MTPLX

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.

  • 2.7k
  • Python
  • Apache-2.0
  • 13 d ago
youssofalTake it
Search GitHub and Hugging Face for flash-next

Get , open it once and sign in. Then come back here and press the button again.

flash-next: open source repos and models on Take My Repo