Command Palette
Search for a command to run...
club-3090
A community-driven configuration repository for deploying LLMs on RTX 3090 hardware with support for multiple inference engines including vLLM, llama
What it is
A community-driven configuration repository for deploying LLMs on RTX 3090 hardware with support for multiple inference engines including vLLM, llama.cpp, and SGLang. Provides model-agnostic recipes and pre-optimized configurations for single and dual-card setups, starting with Qwen 27B variants. Built as an open-source Shell project to democratize LLM serving on consumer-grade GPUs.
HTTP liveness
no probes yetThis URL has not been probed yet.
Observed events
probes · press · GitHub- Jun 1, 2026+23 stars1,215 total
- May 29, 2026+12 stars1,192 total
- May 28, 2026+36 stars1,180 total
- May 26, 2026+114 stars1,144 total
- May 21, 2026+36 stars1,020 total
- May 18, 2026+16 stars984 total
- May 17, 2026+271 stars968 total
- May 10, 2026+92 stars697 total
- May 7, 2026+101 stars605 total
Discussion 0 comments
No comments yet. Be the first!
Not enough observed signals for a Pulse Index (needs 2+ signal families).
567 products launched in 2026 · 100% still active