nunchaku-ai / text-to-image updated 10 months ago

nunchaku-qwen-image-edit

This repository contains Nunchaku-quantized versions of Qwen-Image-Edit, an image-editing model based on Qwen-Image, advances in complex text rendering. It is optimized for efficient inference while maintaining minimal loss in performance.

Params
Context
Downloads 30d
77 K
Likes
121
Commercial use: allowed apache-2.0 Not gated SAFETENSORS 1 languages View on Hugging Face ↗

Download history

daily snapshots · 55 days
▲ 13 K in the last 30 days (19.5%)
78 K58 K
Jul 28Aug 15Sep 2Sep 20

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
model.safetensors fp16 147.6 GB 162.9 GB ❌ Won’t fit
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Licence
apache-2.0
First seen on the Hub
2025-09-10
Training datasets
mit-han-lab/svdquant-datasets
Added to our catalog
2026-07-28
Compare with any text-to-image model