Welcome! Type "help" for available commands.

noonghunna/club-3090: Community recipes for serving LLMs on RTX...

~/bookmarks

/**/

GitHub - noonghunna/club-3090: Community recipes for serving LLMs on RTX 3090. Multi-engine (vLLM, llama.cpp, SGLang) and model-agnostic. Currently shipping Qwen3.6-27B configs for 1× and 2× cards.

github.comSaved May 3, 20269 min

Open Source Software

Summary

This GitHub repo offers Docker configs for running LLMs on RTX 3090s using vLLM or llama.cpp. It focuses on Qwen3.6-27B, supporting single or dual GPU setups with OpenAI-compatible APIs and detailed benchmarks.

Highlights

Multi-engine support for vLLM, llama.cpp, and SGLang.
Optimized for RTX 3090 hardware in 1x, 2x, or cluster setups.
Production-ready configs for Qwen3.6-27B model.
Includes OpenAI-compatible API via Docker Compose.
Provides scaling docs and performance benchmarks.

auto-generated

Preview of GitHub - noonghunna/club-3090: Community recipes for serving LLMs on RTX 3090. Multi-engine (vLLM, llama.cpp, SGLang) and model-agnostic. Currently shipping Qwen3.6-27B configs for 1× and 2× cards.

noonghunna · via GitHub

Context

Audience

AI developers and homelab enthusiasts deploying local LLMs

DomainMachine Learning Infrastructure

Formatopen source repository

Accessopen source

Topics

Local LLM Deployment Llama.cpp GPU Optimization vLLM Large Language Models Serving

View on GitHub All Bookmarks

vLLMllama.cppSGLangQwen3.6-27BRTX 3090Docker Compose

~/bookmarks

GitHub - noonghunna/club-3090: Community recipes for serving LLMs on RTX 3090. Multi-engine (vLLM, llama.cpp, SGLang) and model-agnostic. Currently shipping Qwen3.6-27B configs for 1× and 2× cards.

Summary

Highlights

Context

Topics

Related

GitHub - noonghunna/club-3090: Community recipes for serving LLMs on RTX 3090. Multi-engine (vLLM, llama.cpp, SGLang) and model-agnostic. Currently shipping Qwen3.6-27B configs for 1× and 2× cards.

Summary

Highlights

Context

Topics

Related

~/bookmarks

GitHub - noonghunna/club-3090: Community recipes for serving LLMs on RTX 3090. Multi-engine (vLLM, llama.cpp, SGLang) and model-agnostic. Currently shipping Qwen3.6-27B configs for 1× and 2× cards.

Summary

Highlights

Context

Topics

Related

Discover Similar Content

GitHub - MiaAI-Lab/Qwen3.8-27B-DGX-Spark-RTX-6000: Qwen3.8 27B for DGX Spark / RTX 6000 PRO

GitHub - bilikaz/qwen38-flash-next-recipe: qwen38-flash-next recipe for solo GB10

Qwen3.8-27B - SGLang Documentation

Discover Similar Content

GitHub - noonghunna/club-3090: Community recipes for serving LLMs on RTX 3090. Multi-engine (vLLM, llama.cpp, SGLang) and model-agnostic. Currently shipping Qwen3.6-27B configs for 1× and 2× cards.

Summary

Highlights

Context

Topics

Related

Discover Similar Content

GitHub - MiaAI-Lab/Qwen3.8-27B-DGX-Spark-RTX-6000: Qwen3.8 27B for DGX Spark / RTX 6000 PRO

GitHub - bilikaz/qwen38-flash-next-recipe: qwen38-flash-next recipe for solo GB10

Qwen3.8-27B - SGLang Documentation