peonist-ai / halogen-server
The fastest way to run Qwen3.8 27B on Strix Halo (gfx1151)
Why this job: topics: local-llm, inference-engine, llm-serving
What it does
Every kernel is written for this one GPU and this one model family. No general-purpose runtime, no portability layer, no fallback path — which is why it can do things a general engine cannot, and why it runs on exactly one piece of silicon.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 58 days ago
- Stars
- 158
- +3 this week
- Licence
- Custom
- Read before business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Python
- 71% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 57% closed
- 6 still open
- Pull requests
- 0 merged
- 0 waiting
- Releases
- None
- Never published
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| shawnshekari / strixite | 100 | 6 days ago | AGPL-3.0 | No downloads |
| IIIIIllllIIIIIlllll / Qwenox | 137 | yesterday | AGPL-3.0 | Windows |
| vllm-project / vllm | 96,694 | today | Apache-2.0 | Mac, Linux |
More: languages, topics and project record
Languages
- Python 71%
- Shell 29%
Topics
- amd
- gfx1151
- gpu-inference
- hip
- inference-engine
- llm
- llm-serving
- local-llm
- openai-api
- qwen
- qwen3
- radeon
Project record
- JobLocal LLMs
- StatusListed
- Commits11
- Forks9
- Watching4
- Stars in 28 days+31
- CreatedAug 26, 2026
- First seen by usNov 7, 2026
- CheckedNov 8, 2026