Qwen / text-to-image Open weights updated 1 year ago

Qwen-Image

Name: Qwen-Image
Author: Qwen

💜 Qwen Chat&nbsp&nbsp &nbsp&nbsp🤗 Hugging Face&nbsp&nbsp &nbsp&nbsp🤖 ModelScope&nbsp&nbsp &nbsp&nbsp 📑 Tech Report &nbsp&nbsp &nbsp&nbsp 📑 Blog &nbsp&nbsp 🖥️ Demo&nbsp&nbsp &nbsp&nbsp💬 WeChat (微信)&nbsp&nbsp &nbsp&nbsp🫨 Discord&nbsp&nbsp

Params

20.4 B

Context

—

Downloads 30d

325 K

Likes

2,693

Commercial use: allowed apache-2.0 Not gated SAFETENSORS 2 languages View on Hugging Face ↗

Download history

daily snapshots · 106 days

▲ 56 K in the last 30 days (20.9%)

332 K187 K

Jul 28Sep 1Oct 6Nov 10

Can you run it?

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

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	bf16	57.7 GB	67.0 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

Parameters: 20.4 B
Tensor type: BF16
Licence: apache-2.0
First seen on the Hub: 2025-08-02
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Family

Base model and the most-downloaded derivatives in the catalog.

Derivative Qwen-Image-Lightning lightx2v 246 K Derivative Qwen-Image-GGUF unsloth 136 K Derivative Qwen-Image-GGUF QuantStack 107 K Derivative Qwen-Image-gguf city96 71 K

Compare with any text-to-image model

Popular comparisons

Qwen-Image-2.1 10.2 M Krea-2 4.5 M Qwen-Image-2.1-Uncensored-Quantized 2.5 M Qwen-Image-2.1-Uncensored-GGUF 2.2 M Qwen-Image-2.1-Turbo-GGUF 1.4 M Flux-2-Dev 998 K

Appears in

Commercial-use image models