PrototypeCommon
devnen/qwen3.6-windows-server
One-click Qwen3.6-27B inference on Windows. 158 tok/s on RTX 5090, 72 tok/s on RTX 3090. Native, no WSL, no Docker, no telemetry.
- Owner
- devnen (personal account)
- Stars
- Stars: 230
- Forks
- Forks: 21
- Language
- Python
- License
- None
- Created
- 2026
- Topics
- llm-inferencelocal-llmoffline-aiprivacyqwenqwen3rtx-3090textual-tuivllmwindows
- Tier
- Prototype (100 to 249 ★) What this tier means
More repos by devnen
All 4 repos by devnen- devnen/Chatterbox-TTS-ServerStars: 1,494PythonBeta
- devnen/Dia-TTS-ServerStars: 356PythonAlpha
- devnen/Kitten-TTS-ServerStars: 281PythonAlpha
Nearby in Python
All Python repos- wonderfulearth/primitive-operation-painterStars: 230PythonPrototype
- any2any-mllm/Omni-IO-SkillStars: 230PythonPrototype
- Tencent-Hunyuan/Hy-SimulMTStars: 230PythonPrototype
- eyeseast/python-tablefuStars: 230PythonPrototype
- wardi/speedometerStars: 230PythonPrototype
- craigds/django-typed-modelsStars: 230PythonPrototype