RCEpic
noonghunna/club-3090
Community recipes for serving LLMs on RTX 3090/4090/5090 CUDA gpus. Multi-engine (vLLM, sglang, llama.cpp and other custom engines) and model-agnostic. Currently shipping Qwen3.8-27B Qwen3.6 35B Gemma 4 26B Gemma 4 31B configs for 1×/2×/4x/8x cards.
- Owner
- noonghunna (personal account)
- Stars
- Stars: 2,474
- Forks
- Forks: 169
- Language
- Python
- License
- Apache-2.0
- Created
- 2026
- Tier
- RC (2,000 to 4,999 ★) What this tier means
More repos by noonghunna
All 2 repos by noonghunna- noonghunna/qwen36-27b-single-3090Stars: 119ShellPrototype
Nearby in Python
All Python repos- olivierkes/manuskriptStars: 2,476PythonRC
- china-testing/python-api-tesingStars: 2,476PythonRC
- xingyizhou/CenterTrackStars: 2,474PythonRC
- microsoft/PIKE-RAGStars: 2,473PythonRC
- mavlink/mavlinkStars: 2,472PythonRC
- pycrypto/pycryptoStars: 2,471PythonRC