local-ai

Club 3090

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
2,206 stars138 forksPythonUpdated 9/8/2026100% free · open source
What it does

Club-3090 provides community-driven recipes for serving large language models on NVIDIA RTX 3090, 4090, and 5090 CUDA GPUs, supporting multiple engines and models

When to use it
  • You need to deploy LLMs on a local machine with an RTX 3090, 4090, or 5090 GPU
  • You want to use a specific LLM model like Qwen3.6 or Gemma 4 with a multi-engine setup
  • You require a model-agnostic solution for serving LLMs on your GPU
Ready-to-paste prompt
python run.py --config configs/qwen3.6-27b.json --prompt 'Write a short story about a character who discovers a hidden world'
Heads up: Ensure you have the necessary CUDA version installed, as the club-3090 recipes are designed to work with specific CUDA versions, and incompatible versions may cause errors or performance issues
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

✅ Light setup

Installs with a command or two; your AI agent can do it for you.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/club-3090 && curl -fsSL https://workflowstacks.com/api/skills/club-3090/claude-skill -o ~/.claude/skills/club-3090/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

Quick Actions
Details
Creator
noonghunna
Language
Python
Category
local-ai
Published
4/28/2026

Are you the creator of this tool? Claim your listing → and earn 85% of every sale.