github.com 引用 近期 代码仓库
GitHub - 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.
club-3090 汇集在 RTX 3090/4090/5090 上本地部署 LLM 的配置、补丁与实测数据。
资源信息
- 域名
- github.com
- 内容类型
- 代码仓库（repository）
- 主题
- 立场
- 引用（reference）
- 提及
- 5 次提及，5 位提及者
- 合集
- 近期（recent）
- 提及年份
- 2026
- 综合推荐分
- 4.4
推荐理由
Mentions club 3090 as a resource he has heard about, without personal experience.
HN 评论原话
“I've heard that club 3090 makes that relatively straightforward”
网页原文证据
Recipes for serving LLMs locally on RTX 3090s (and other NVIDIA cards)
网页抓取状态
成功（ok）