unsloth / text-to-image updated 8 months ago

Qwen-Image-GGUF

> [!NOTE] > This is a GGUF quantized version of Qwen-Image. > unsloth/Qwen-Image-GGUF uses Unsloth Dynamic 2.0 methodology for SOTA performance. Important layers are upcasted to higher precision.

Params
Context
Downloads 30d
32 K
Likes
33
Commercial use: allowed apache-2.0 Not gated GGUF 2 languages View on Hugging Face ↗

Download history

tracking started — chart appears after 7 days of snapshots (6 recorded)
32 K downloads in the last 30 days

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
qwen-image-Q2_K.gguf Q2_K 7.2 GB 8.4 GB ✅ Runs comfortably
qwen-image-Q3_K_S.gguf Q3_K_S 9.0 GB 10.4 GB ✅ Runs comfortably
qwen-image-Q3_K_M.gguf Q3_K_M 9.7 GB 11.2 GB ✅ Runs comfortably
qwen-image-Q3_K_L.gguf Q3_K_L 10.4 GB 12.0 GB ✅ Runs comfortably
qwen-image-Q4_0.gguf Q4_0 11.9 GB 13.5 GB ✅ Runs comfortably
qwen-image-Q4_1.gguf Q4_1 12.8 GB 14.6 GB ✅ Runs comfortably
qwen-image-Q4_K_M.gguf Q4_K_M 13.1 GB 14.9 GB ✅ Runs comfortably
qwen-image-BF16.gguf GGUF 40.9 GB 45.5 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
2025-12-19
Base model
Qwen-Image
Training datasets
undisclosed
Added to our catalog
2026-09-15

Family

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

Compare with any text-to-image model