noonghunna/club-3090
Daily ranking profile for noonghunna/club-3090 in AI Rank.
Community recipes for serving LLMs on RTX 3090. Multi-engine (vLLM, llama.cpp, SGLang) and model-agnostic. Currently shipping Qwen3.6-27B configs for 1×...
- Stars: 872
- Forks: 47
- Language: Python
- Category: Infrastructure
- Subcategory: Deploy & Serve,Inference service optimization
- Keywords: Containers, DevOps, Inference optimization, LocalAI