← Back to Discover
noonghunna

noonghunna/club-3090

PythonApache-2.0activerising
76Health

Community recipes for serving LLMs on RTX 3090/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.

Stars1.1k
Forks55
Open Issues12
Contributors55
Last Push0d ago

Health Breakdown

Activity
25
Community
13
Maintenance
13
Popularity
25
View on GitHub ↗Issues (12) ↗Pull Requests ↗Wiki ↗

Community

noonghunna
noonghunna/club-3090
PythonApache 2.0
76

Community recipes for serving LLMs on RTX 3090/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.

activerising
1.1k55 contributors0d ago

More Python repos

sciencepal
sciencepal/sciencepal
Woooh, it's just me, myself and I
15499
WCGKING
WCGKING/BrandrdXMusic
ᴅɪꜱᴄᴏᴠᴇʀ ᴛʜᴇ ᴇɴᴄʜᴀɴᴛɪɴɢ ᴡᴏʀʟᴅ ᴏꜰ ᴍᴜꜱɪᴄ ᴡɪᴛʜ ⛦🦋ʙʀᴀɴᴅʀᴅ ❥! ᴛʜɪꜱ ᴘʏᴛʜᴏɴ-ʙᴀꜱᴇᴅ ᴛᴇʟᴇɢʀᴀᴍ ᴍᴜꜱɪᴄ ʙᴏᴛ, ᴘᴏᴡᴇʀᴇᴅ ʙʏ ᴘʏʀᴏɢʀᴀᴍ ᴠ2, ʙʀɪɴɢꜱ ʜᴀʀᴍᴏɴʏ ᴛᴏ ʏᴏᴜʀ ᴄʜᴀᴛꜱ. ᴇɴᴊᴏʏ ꜱᴇᴀᴍʟᴇꜱꜱ ᴍᴜꜱɪᴄ ꜱʜᴀʀɪɴɢ ᴀɴᴅ ꜱᴛʀᴇᴀᴍɪɴɢ ɪɴ ꜱᴛʏʟᴇ.
10395
haoyiyin
haoyiyin/basjoo
Open-source AI customer support platform — RAG knowledge base, multi-provider LLM agents, embeddable chat widget. FastAPI + Next.js + R2R + pgvector.
9994