Qwen-Image-2.1-Turbo-GGUF
GGUF quants of Qwen/Qwen-Image-2.1-Turbo, the 8-step distilled Qwen-Image-2.1 (7B DiT). Converted with stable-diffusion.cpp from the official diffusers weights on release day. Every quant is tested on a single RTX 3060 12GB.
Params
—
Context
—
Downloads 30d
234 K
Likes
7
Download history
daily snapshots · 8 days234 K64 K
Oct 17Oct 19Oct 22Oct 24
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-2.1-turbo-Q2_K.gguf | Q2_K | 2.4 GB | 3.1 GB | ✅ Runs comfortably |
| qwen-image-2.1-turbo-Q3_K.gguf | Q3_K | 3.1 GB | 3.9 GB | ✅ Runs comfortably |
| qwen-image-2.1-turbo-Q3_K_S.gguf | Q3_K_S | 3.1 GB | 3.9 GB | ✅ Runs comfortably |
| qwen-image-2.1-turbo-Q4_K.gguf | Q4_K | 4.1 GB | 5.0 GB | ✅ Runs comfortably |
| qwen-image-2.1-turbo-Q4_K_S.gguf | Q4_K_S | 4.1 GB | 5.0 GB | ✅ Runs comfortably |
| qwen-image-2.1-turbo-Q5_0.gguf | Q5_0 | 4.9 GB | 5.9 GB | ✅ Runs comfortably |
| qwen-image-2.1-turbo-Q6_K.gguf | Q6_K | 5.9 GB | 7.0 GB | ✅ Runs comfortably |
| qwen-image-2.1-turbo-F16.gguf | GGUF | 14.2 GB | 16.2 GB | ✅ Runs comfortably |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Specifications
- Licence
- other
- First seen on the Hub
- 2026-10-09
- Training datasets
- undisclosed
- Added to our catalog
- 2026-10-17
Compare with any text-to-image model