peonist-ai /
halogen-server
The fastest way to run Qwen3.8 27B on Strix Halo (gfx1151)
Updated 6 min ago
Why now
+15 stars gained this week
2× its usual pace
Stars gained each day, last 30 days
Usual pace · 1 / day
Oct 4Oct 19Today
This week Before Usual pace
In short
A Python inference engine that runs the Qwen3.8 27B model on AMD Strix Halo GPUs using custom kernels built for that single hardware. It exposes an OpenAI-compatible API for local serving.
Summary written by AI from the repository’s description and README.
peonist-ai / halogen-server
View on GitHub(opens in new tab)