Qwen-Image-2.1-Turbo-Uncensored-GGUF
Qwen-Image's text encoder, Qwen3-VL-8B-Instruct, with its refusal direction projected out: a drop-in --llm for stable-diffusion.cpp next to our Turbo denoiser GGUFs. Below, exactly which part is uncensored and what that does to the pictures. The measurements are public. As a chat model, the encoder's refusals fall from 88.9% to 1.2% in English and from 38% to 0% in Russian on held-out prompts. MMLU is unchanged: 77.3...
Params
8.8 B
Context
—
Downloads 30d
453 K
Likes
605
Download history
daily snapshots · 12 days453 K101 K
Oct 12Oct 16Oct 20Oct 23
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-Uncensored-AD-Q2_K.gguf | Q2_K | 3.3 GB | 5.5 GB | ✅ Runs comfortably |
| Qwen-Image-2.1-Turbo-Uncensored-AD-Q3_K.gguf | Q3_K | 4.2 GB | 6.4 GB | ✅ Runs comfortably |
| Qwen-Image-2.1-Turbo-Uncensored-AD-Q4_K.gguf | Q4_K | 5.3 GB | 7.6 GB | ✅ Runs comfortably |
| Qwen-Image-2.1-Turbo-Uncensored-AD-Q5_K.gguf | Q5_K | 6.3 GB | 8.7 GB | ✅ Runs comfortably |
| Qwen-Image-2.1-Turbo-Uncensored-AD-Q6_K.gguf | Q6_K | 7.5 GB | 10.1 GB | ✅ Runs comfortably |
| Qwen-Image-2.1-Turbo-Uncensored-Q8_0.gguf | Q8_0 | 8.7 GB | 11.4 GB | ✅ Runs comfortably |
| Qwen-Image-2.1-Turbo-Uncensored-BF16.gguf | GGUF | 16.4 GB | 19.8 GB | ⚠️ Tight — reduce context |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Specifications
- Parameters
- 8.8 B
- Licence
- apache-2.0
- First seen on the Hub
- 2026-10-09
- Base model
- Qwen3-VL-8B-Instruct
- Training datasets
- undisclosed
- Added to our catalog
- 2026-10-12
Family
Base model and the most-downloaded derivatives in the catalog.
Compare with any text-to-image model
Popular comparisons
Appears in