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
20.4 B
Context
—
Downloads 30d
136 K
Likes
36
Download history
daily snapshots · 57 days
▲ 55 K in the last 30 days (68.9%)
136 K82 K
Oct 12Oct 22Nov 1Nov 10
136 K24 K
Sep 15Oct 4Oct 23Nov 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 |
|---|---|---|---|---|
| qwen-image-Q2_K.gguf | Q2_K | 7.7 GB | 12.1 GB | ✅ Runs comfortably |
| qwen-image-Q3_K_S.gguf | Q3_K_S | 8.8 GB | 13.2 GB | ✅ Runs comfortably |
| qwen-image-Q3_K_M.gguf | Q3_K_M | 9.0 GB | 13.5 GB | ✅ Runs comfortably |
| qwen-image-Q3_K_L.gguf | Q3_K_L | 10.3 GB | 14.9 GB | ✅ Runs comfortably |
| qwen-image-Q4_0.gguf | Q4_0 | 11.9 GB | 16.6 GB | ✅ Runs comfortably |
| qwen-image-Q4_1.gguf | Q4_1 | 12.8 GB | 17.7 GB | ✅ Runs comfortably |
| qwen-image-Q4_K_M.gguf | Q4_K_M | 12.8 GB | 17.7 GB | ✅ Runs comfortably |
| qwen-image-BF16.gguf | GGUF | 40.9 GB | 48.5 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
- Parameters
- 20.4 B
- 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
Compare with any text-to-image model