PrototypeCommon
peonist-ai/halogen-server
The fastest way to run Qwen3.8 27B on Strix Halo (gfx1151)
- Owner
- peonist-ai (organization)
- Stars
- Stars: 154
- Forks
- Forks: 7
- Language
- Python
- License
- None
- Created
- 2026
- Topics
- amdgfx1151gpu-inferencehipinference-enginellmllm-servinglocal-llmopenai-apiqwen
- Tier
- Prototype (100 to 249 ★) What this tier means
More repos by peonist-ai
All 2 repos by peonist-ai- peonist-ai/halogen-flash-serverStars: 1,200ShellBeta
Nearby in Python
All Python repos- zzusec/forkiqStars: 154PythonPrototype
- xkx121029/mcd-vibe-commitStars: 154PythonPrototype
- Qingyang-Lucas-Fang/OpenAssemblerStars: 154PythonPrototype
- notanumber/xapian-haystackStars: 154PythonPrototype
- redhat-imaging/imagefactoryStars: 154PythonPrototype
- shazow/unstdlib.pyStars: 154PythonPrototype