rtx-5090 repositories
Trending repositories tagged rtx-5090, ranked by trending score. Updated daily.
-
1
NODIX-TECH/DLSS-5-MANAGER
THE FIRST DLSS 5 MANAGER
GitHub · F# · 1,654 stars · 79 forks · +20 stars in 24 hours · Trending score 2.45
-
2
perkel666/MegaCapybara
The fastest inference engine for Qwen3.8-27B on the NVIDIA RTX 5090: up to 500 tokens/s for one agent and up to 2,000 tokens/s for many, contexts up to 1M tokens, and a launcher that shows what every setting costs. Windows and Linux.
GitHub · 85 stars · 1 forks · +33 stars in 24 hours · Trending score 2.34
-
3
autonomous-ai/Personal-AI-Computer
Open-source AI computer builds, from 2-GPU desktops to 8-GPU servers: CAD, BOM, BIOS and build guides. Get the case kit with PCIe risers, or ask us for a free fit check.
GitHub · 1,600 stars · 179 forks · +1 stars in 24 hours · Trending score 1.92
-
4
cc2025cheng/Stop-Manually-Refreshing-AutoDL-GPU
AutoDL GPU 监控与自动开机:别再手动刷新抢卡了!设好型号(4090、5090 等都可以)、地区和镜像并授权,空卡一出现就自动创建并开机,也能同地区克隆换卡。本地运行,免费开源,非官方工具。AutoDL GPU monitor: auto-create and start an instance when a GPU frees up.
GitHub · JavaScript · 40 stars · 3 forks · +10 stars in 24 hours · Trending score 1.77
-
5
xilla420/dlss5-wow-sidecar
DLSS 5 Neural Rendering for World of Warcraft (WoW) on NVIDIA RTX 40/50 — a safe overlay with no DLL injection, no hooks and no ReShade next to Wow.exe. Free and open source.
GitHub · C++ · 42 stars · 13 forks · +3 stars in 24 hours · Trending score 1.15
-
6
gpillon/ignis
An inference engine for NVIDIA RTX card card family, built for a coding agent and its subagents, and a companion that listens, reads and draws: Qwen3.8 27B and 125B Flash-Next MoE, Qwen-Image-2.1, Qwen3-ASR on the CPU. OpenAI-compatible API and Playground in one binary.
GitHub · Rust · 70 stars · 9 forks · +3 stars in 24 hours · Trending score 1.14
-
7
humza-khalid/12vhpwr-guard
Standalone per-pin 12VHPWR overcurrent watchdog for ASUS ROG Astral GPUs. Shuts down your PC before the connector melts.
GitHub · Python · 123 stars · 11 forks · +4 stars in 24 hours · Trending score 1.05
-
8
lifeidle/comfyui-5090-laptop-24gb-minimax-h3-qwen-image-wan2.2
RTX 5090 Laptop (24GB) + ComfyUI: 12 model lines / 21 measured configs — MiniMax H3, Wan 2.2, Qwen-Image 2512, HunyuanVideo 1.5, FLUX.2 Klein, Z-Image-Turbo, LTX-Video, ACE-Step 1.5, YuE2, Stable Audio 3, Hunyuan3D 2.1, ERNIE-Image. A controlled A/B proves NVFP4 beats INT8. Bilingual 中文/English, licence-verified.
GitHub · HTML · 27 stars · 0 forks · +2 stars in 24 hours · Trending score 1.01
-
9
adrienbrault/qwen3.8-27b-rtx5090
Qwen3.8-27B on 2× RTX 5090 · 1.49M KV · code/prose t/s: c1 264/216, c16 2,649/2,240 · NVFP4 + vLLM + MTP
GitHub · Python · 28 stars · 4 forks · +3 stars in 24 hours · Trending score 0.91
-
10
gittensor-ai-lab/sparkinfer
Fastest MoE/LLM inference runtime for consumer and edge Blackwell GPUs. SN74 on Gittensor.
GitHub · C++ · 93 stars · 82 forks · +3 stars in 24 hours · Trending score 0.90
-
11
avifenesh/memra
Memra is a Rust + CUDA LLM inference engine with hand-written kernels, NVFP4 and mixed-precision execution, and correctness gates scoped to each model and GPU
GitHub · Rust · 8 stars · 1 forks · +1 stars in 24 hours · Trending score 0.64
-
12
headpiece747/ninfer-5090-windows
Native Windows port of NInfer engine for RTX 5090. Features Qwen3.8-27B with QUASAR and NInfer models, MTP/DFlash2 with vision and 262,144 context
GitHub · C++ · 95 stars · 18 forks · 0 stars in 24 hours · Trending score 0.57
-
13
kacper-daftcode/vLLM-Moet
Frontier MoE models on RTX PRO 6000 / RTX 5090 (sm_120): DeepSeek-V4.1-Flash on 4x RTX PRO 6000, as a GPU+CPU hybrid on 4x RTX 5090, and 2-bit experts on vLLM v0.24.0
GitHub · Sass · 579 stars · 49 forks · 0 stars in 24 hours · Trending score 0.49
-
14
nibor1896/crow-nest
Rust + CUDA inference engine for Crow on one RTX 5090: GLM-5.3-Flash, Qwen3.8-Flash-Next (MoE) and the dense Qwen3.8-27B as CNQ containers, own kernels, MTP speculative decoding, vision, OpenAI-compatible serve. Windows and Linux.
GitHub · Rust · 6 stars · 0 forks · +1 stars in 24 hours · Trending score 0.46
-
15
jamesarslan/local-ai-coding-setup
Local AI coding pipeline on an RTX 5090: llama.cpp, Qwen3.5/3.6 MoE, Gemma 4, TurboQuant KV, OpenCode, Claude Code, MCP. 188 t/s (Qwen3.5-35B-A3B, mainline, f16 KV); ~177 t/s (Qwen3.6-35B-A3B, turbo3, TLA=2). Optional cloud GPU server; default config uses hosted Context7 docs MCP.
GitHub · Shell · 22 stars · 4 forks · 0 stars in 24 hours · Trending score 0.22
-
16
kekzl/imp
Run large AI chat models privately on your own NVIDIA RTX 50 or RTX PRO graphics card. On one RTX 5090, Qwen3.8-27B writes about 70 words per second, 1.4x faster than vLLM. Even a model almost four times larger than the card's memory runs. Works with apps made for ChatGPT or Claude. Starts with one docker command.
GitHub · C++ · 79 stars · 6 forks · 0 stars in 24 hours · Trending score 0.10
-
17
alphastorm/omp-ninfer
Durable local inference for Oh My Pi: NInfer + Qwen3.8 27B on one RTX 3090/4090/5090, with restart-resumable OpenAI Responses state.
GitHub · Python · 50 stars · 5 forks · 0 stars in 24 hours · Trending score 0.05