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.
☆1,868Aug 2, 2026Updated this week
Alternatives and similar repositories for club-3090
Users that are interested in club-3090 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆118Apr 28, 2026Updated 3 months ago
- LLM speculative inference server for consumer hardware & heterogeneous computing☆2,712Updated this week
- SNDR Core Engine (Genesis) — vLLM runtime patch-overlay for Qwen3.6 + Gemma4 on consumer NVIDIA (Ampere sm_86, 2× A5000/3090). Qwen3.6-35…☆131Updated this week
- Qwen3.6-27B on dual RTX 3090 — TP=2 recipe, vLLM nightly, MTP + fp8 KV, validated for concurrent serving☆56Apr 28, 2026Updated 3 months ago
- Single-file installer for a club-3090 webserver providing an admin control panel, a reverse proxy that automatically routes requests to t…☆22Jul 8, 2026Updated 3 weeks ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- KVarN, KV cache precision tail, low-bit quants in llama.cpp for longer context of better precision in the same VRAM☆829Updated this week
- Reliable model swapping for any local OpenAI/Anthropic compatible server - llama.cpp, vllm, etc☆5,251Updated this week
- vLLM Docker Container for Qwen3.6 27b☆51Jun 15, 2026Updated last month
- NVIDIA Linux open GPU with P2P support☆377Jul 13, 2026Updated 3 weeks ago
- llama.cpp fork with additional SOTA quants and improved performance☆2,990Updated this week
- llama.cpp/ik_llama.cpp launcher: loads big MoE models across mismatched multi-GPU rigs by exact VRAM math.☆259Updated this week
- A harness optimized to smaller LLMs☆2,240Updated this week
- Experimental llama.cpp fork for inference research and development☆725Updated this week
- One-click Qwen3.6-27B inference on Windows. 158 tok/s on RTX 5090, 72 tok/s on RTX 3090. Native, no WSL, no Docker, no telemetry.☆227May 14, 2026Updated 2 months ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Reproducible llama.cpp configs + per-category quality benches for Qwen3.6-27B on a single RTX 4090. Winners, dead ends, and the silent-co…☆23Apr 26, 2026Updated 3 months ago
- An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs☆1,106Updated this week
- RTX 6000 Pro Wiki — Running Large LLMs (Qwen3.5-397B, Kimi-K2.5, GLM-5) on PCIe GPUs without NVLink☆763Updated this week
- ☆17Jul 21, 2026Updated last week
- ☆44May 4, 2026Updated 3 months ago
- A vLLM patch + hand‑written SM120 SASS kernels: 2‑bit MoE experts + an FP4 "delta" cache that recovers precision — matching the official …☆491Updated this week
- An all-in-one, pure C++ inference engine for audio models, powered by ggml. Supports TTS, STT, VAD, voice conversion, music generation, a…☆1,130Updated this week
- LLM inference in C/C++☆2,226Updated this week
- ☆15Apr 27, 2026Updated 3 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- AI coding agent optimized for small LLMs. 87% benchmark with 4B-active model.☆1,997Jul 25, 2026Updated last week
- Core, junction, and VRAM temps for GDDR6, GDDR6X, GDDR7 NVIDIA GPUs in Linux☆88Updated this week
- DFlash: Block Diffusion for Flash Speculative Decoding☆5,562May 10, 2026Updated 2 months ago
- Structured Chain-of-Thought☆219May 16, 2026Updated 2 months ago
- llama.cpp fork with TQ3_1S/4S CUDA kernels — 3.5-bit WHT quantization achieving Q4s quality at 10% smaller size. Based on RaBitQ-inspired…☆222Updated this week
- Validated recipe for serving Qwen3.6-27B on a single RTX 5090 — full OpenAI API, vision, tool calling, MTP spec-decode☆69Apr 29, 2026Updated 3 months ago
- Control panel for VLLM, Sglang, llama.cpp, exllamav3☆1,526Updated this week
- Deploy concurrent Hermes Agent workers on unified-memory GPUs (GB10, DGX Spark) for maximum total tok/s. Profile-isolated, kanban-coordin…☆79Jul 18, 2026Updated 2 weeks ago
- Interactive Jacobian-Lens visualizer and live steerer for GGUF models on llama.cpp☆80Jul 12, 2026Updated 3 weeks ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- KVarN is a native vLLM KV-cache quantization backend for your agents: 3-5x more context, throughput above FP16, and FP16-level accuracy. …☆452Jun 22, 2026Updated last month
- A pixel art space shooter built entirely by a 9B AI model on a single RTX 3060. Zero hand-written code.☆96Mar 19, 2026Updated 4 months ago
- ik_llama.cpp's Thireus fork with release builds for macOS/Windows/Ubuntu CPU, Vulkan and CUDA☆167Updated this week
- Stop configuring your AI stack. Start using it. One command brings a complete pre-wired LLM stack with hundreds of services to explore.☆3,152Updated this week
- Using LLMs for iteratively exploring the solution search space at scale.☆740Updated this week
- Test LLMs on real tasks. Compare models side-by-side.☆393Jun 16, 2026Updated last month
- Pipeline-parallel LLM inference across GPUs on separate machines.☆435Updated this week