#5959th of 89 in Image and videoFor image, video and design, image and design
nunchaku
4-bit SVDQuant inference engine for FLUX, Qwen-Image and SANA diffusion models
- Stars
- 4k
- License
- Apache-2.0
- Last commit
- Sep 2026
- Last release
- Jan 2026
- Language
- Python
3,759 on 25 Apr 20263,969 on 14 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Nunchaku is a Python inference engine that runs diffusion models quantized to 4-bit weights and activations using SVDQuant, with fused kernels for the low-rank branch. The README reports a 3.6x memory reduction on 12B FLUX.1-dev and about 3x speedup over an NF4 W4A16 baseline on RTX 4090. It supports INT4 and NVFP4 (RTX 5090), LoRA, ControlNet, CPU offloading, and a ComfyUI plugin.
Who it is for: Self-hosters running diffusion models on consumer NVIDIA GPUs with limited VRAM
Strengths
- Reported 3.6x memory reduction and about 3x speedup over NF4 on FLUX.1-dev
- Supports INT4 and NVFP4 precision, including 20-series and RTX 5090 GPUs
- Offloading cuts Qwen-Image VRAM to about 3 GiB and FLUX to 4 GiB
- ComfyUI plugin, Gradio demo apps and Python examples for many models
Weaknesses
- Needs NVIDIA GPU; no CPU-only or non-NVIDIA backend is described
- Models must be pre-quantized, or quantized separately with DeepCompressor
- Covers diffusion models only; no LLM serving or HTTP API
- Last tagged release is January 2026, while main has later commits
What it needs
- GPU required
- Needs PyTorch, ComfyUI (optional plugin), DeepCompressor (optional, for quantization)
- Models: FLUX.1-dev, FLUX.1-Kontext, FLUX.1-Krea-dev, FLUX.1-tools, Qwen-Image
What changed
From the release notes. No flag means the note does not say so, not that the upgrade is safe.
Also in Image and video
See all 89| Rank | Project | Score |
|---|---|---|
| 1 | frigateLocal NVR with realtime object detection for IP cameras | 93 out of 100 |
| 2 | MoneyPrinterTurboGenerates short videos from a topic, with script, footage, voiceover and subtitles | 88 out of 100 |
| 3 | toonflow-appInfinite-canvas tool for AI short drama and comic video production | 88 out of 100 |
| #4 | InvokeAIWeb UI for diffusion image generation with inpainting canvas and node workflows | 87 out of 100 |
| #5 | ComfyUINode-graph editor for running diffusion image, video, audio and 3D workflows | 85 out of 100 |