🌱 Open Source
Back to Open Source

🐙 GitHub Detail

C

noonghunna/club-3090

By noonghunna

Community recipes for serving LLMs on RTX 3090/4090/5090 CUDA gpus. Multi-engine (vLLM, llama.cpp, ik_llama) and model-agnostic. Currently shipping Qwen3.6-27B Qwen3.6 35B Gemma 4 26B Gemma 4 31B configs for 1× and 2× cards.

GitHub Python Apache License 2.0 Updated 13 Jun 2026

Live Snapshot

Stars

1,324

🍴

Forks

71

📄

License

Apache License 2.0

🧩

Type

Python

📘

About this open-source project

Live information fetched from GitHub.

Community recipes for serving LLMs on RTX 3090/4090/5090 CUDA gpus. Multi-engine (vLLM, llama.cpp, ik_llama) and model-agnostic. Currently shipping Qwen3.6-27B Qwen3.6 35B Gemma 4 26B Gemma 4 31B configs for 1× and 2× cards.

🌿

Default Branch

master

🐞

Open Issues

17

👀

Watchers

1,324