noonghunna/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 Qwen3.6 35B Gemma 4 26B Gemma 4 31B configs for 1× and 2× cards.
Related Stories
The memory layer that never calls an LLM: what that buys, and what it costs
Dev.to
2 days ago
Does it still make sense to learn how to code?
Dev.to
2 days ago
Why Kimi K3 Still Can't Do What Einstein Did
Dev.to
3 days ago
Your Face on a World Cup Sticker: Our Nano Banana Story
Dev.to
4 days ago
Understanding Over Origin
Dev.to
4 days ago