BetaRare
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.
- Owner
- peonist-ai (organization)
- Stars
- Stars: 1,200
- Forks
- Forks: 80
- Language
- Shell
- License
- None
- Created
- 2026
- Topics
- amdgfx1151gpu-inferencehipinference-enginellmllm-servinglocal-llmlong-contextmixture-of-experts
- Tier
- Beta (700 to 1,999 ★) What this tier means
More repos by peonist-ai
All 2 repos by peonist-ai- peonist-ai/halogen-serverStars: 154PythonPrototype
Nearby in Shell
All Shell repos- bitol-io/open-data-contract-standardStars: 1,203ShellBeta
- Mr-MIBonk/M.I.B._More-Incredible-BashStars: 1,201ShellBeta
- junegunn/fzf-git.shStars: 1,200ShellBeta
- elementary/osStars: 1,199ShellBeta
- CompSciLauren/awesome-git-hooksStars: 1,198ShellBeta
- timothystewart6/techno-tim.github.ioStars: 1,198ShellBeta