OneDecision VisionGuard 9B SFT needs about 7.2 GB of memory at Q4_K_M (a 5.6 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 12 quants, from 3.8 GB (Q2_K) to 17.9 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Dense 9B multimodal image classification for content safety
OneDecision VisionGuard 9B SFT is a dense 9‑billion‑parameter multimodal model based on Qwen/Qwen3.5‑9B. It classifies images as Safe or NSFW, focusing on sensual and other sensitive content. The model outputs a structured JSON with scene description, classification, and reasoning.
Good at
- NSFW image classification
- Dress‑code and pose analysis
- Structured JSON output
Limits
- No vision support beyond image classification
- Requires large VRAM for higher quants
- Apache‑2.0 license limits commercial use
Best for
- Content‑safety pipelines
- Moderation tools
- Research on visual content analysis
Who it’s for. Developers building moderation systems or researchers studying visual content safety. The model is intended for research and content‑safety classification only.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 3.8 GB | 5.4 GB | Fits | Get file → | |
| Q3_K_S | 4.3 GB | 5.8 GB | Fits | Get file → | |
| Q3_K_M | 4.6 GB | 6.2 GB | Fits | Get file → | |
| Q3_K_L | 4.9 GB | 6.5 GB | Fits | Get file → | |
| IQ4_XS | 5.2 GB | 6.8 GB | Fits | Get file → | |
| Q4_K_S | 5.4 GB | 6.9 GB | Fits | Get file → | |
| Q4_K_M | 5.6 GB | 7.2 GB | Tight | Get file → | |
| Q5_K_S | 6.3 GB | 7.9 GB | Tight | Get file → | |
| Q5_K_M | 6.5 GB | 8.0 GB | Too big | Get file → | |
| Q6_K | 7.4 GB | 8.9 GB | Too big | Get file → | |
| Q8_0 | 9.5 GB | 11.1 GB | Too big | Get file → | |
| F16 | 17.9 GB | 19.5 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (est. 7.2 GB) or Q5_K_S (est. 7.9 GB). If 12 GB VRAM is available, Q6_K (est. 8.9 GB) or Q8_0 (est. 11.1 GB) provide higher fidelity. Larger models like F16 (est. 19.5 GB) require substantial memory and are not recommended for typical setups.
What GPU do you need for OneDecision VisionGuard 9B SFT?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is Q3_K_S (4.3 GB file, about 5.8 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_K_M (6.5 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (9.5 GB file, about 11.1 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (9.5 GB file, about 11.1 GB in use).
- 24 GB VRAM: the best quant that fits is F16 (17.9 GB file, about 19.5 GB in use).
Which OneDecision VisionGuard 9B SFT quant should you choose?
Q4_K_M is the usual starting point for OneDecision VisionGuard 9B SFT: it balances file size and quality well. Here it is a 5.6 GB file.
The Q8_0 file is 9.5 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q2_K at 3.8 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about OneDecision VisionGuard 9B SFT
How much VRAM does OneDecision VisionGuard 9B SFT need?
About 7.2 GB at Q4_K_M with an 8K context window. That is the 5.6 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run OneDecision VisionGuard 9B SFT on an 8 GB GPU?
Yes, with Q5_K_M: the 6.5 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of OneDecision VisionGuard 9B SFT GGUF?
It depends on the quant: Q2_K is 3.8 GB, Q3_K_S is 4.3 GB, Q3_K_M is 4.6 GB, Q3_K_L is 4.9 GB, IQ4_XS is 5.2 GB, Q4_K_S is 5.4 GB and 6 more.
What context length does OneDecision VisionGuard 9B SFT support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download OneDecision VisionGuard 9B SFT GGUF?
The files are on Hugging Face in the mradermacher/OneDecision-VisionGuard-9B-SFT-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does OneDecision VisionGuard 9B SFT use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run this model on 8 GB VRAM?
Yes, the Q4_K_M quant uses approximately 7.2 GB of VRAM at 8k context, which fits within an 8 GB limit.
Does the model support text generation?
No, it is a multimodal image classification model and does not generate text beyond structured JSON output.
What license applies to this model?
The model is released under the Apache‑2.0 license, which allows modification and redistribution under its terms.