# club-3090

11 Hacker News commenters recommended club-3090 and 1 criticized it, November 2025 to November 2026. It was recommended in 6 of 13 months. It meets the Hacker Approved badge rule.

**Verdict:** People recommend it for verified configs and writeups for running local Qwen and Gemma models on one or two GPUs, with documented context window tradeoffs.

## Why people recommend it

- Verified setups for Qwen and Gemma (3 comments): "Qwen3.6 27b has been rock solid using club 3090's single card setup for agentic use" ([source](https://news.ycombinator.com/item?id=48558426)) "I'd jump right into verified set-ups and writeups, like this one" ([source](https://news.ycombinator.com/item?id=48583722)) "optimized configs for Qwen and Gema models" ([source](https://news.ycombinator.com/item?id=48725094))
- Simplifies installing local LLMs on GPUs (2 comments): "I've heard that club 3090 makes that relatively straightforward" ([source](https://news.ycombinator.com/item?id=48763815)) "Club 3090 will make installing llm easier, for 1 or more cards." ([source](https://news.ycombinator.com/item?id=48962977))
- Documents context window tradeoffs (2 comments): "fast inference at the cost of a reduced 102k context window" ([source](https://news.ycombinator.com/item?id=48780586)) "Full 262k context, usable in oh-my-pi." ([source](https://news.ycombinator.com/item?id=48061885))
- Referenced for alternative setups (2 comments): "I need to try out some of the other set ups mentioned in this repo for increased TPS." ([source](https://news.ycombinator.com/item?id=47964824)) "using the config from https://github.com/noonghunna/club-3090" ([source](https://news.ycombinator.com/item?id=49299848))

## Cite as

Hacker Approved, "club-3090", https://hackerapproved.com/p/club-3090/ (counts from 1,795,640 Hacker News comments, November 2025 to November 2026).