peonist-ai/halogen-flash-server

Local inference that behaves like a frontier API: Qwen3.8-Flash-Next on AMD Strix Halo plus small NPU models, over the OpenAI and Anthropic APIs on one port.

3 best points · 0 comments · 1 Hacker News post · 1,248 GitHub stars · View on GitHub

Hacker News discussions

• Halogen – Fastest Way to Run Qwen3.8-Flash-Next on AMD Strix Halo (3 points, 0 comments, by rdslw, 2026-09-30)