VisionGuardrail 4B needs about 4.3 GB of memory at Q4_K_M (a 2.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 10 quants, from 2.1 GB (Q3_K_S) to 8.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
VisionGuardrail 4B – multimodal content‑safety classifier
VisionGuardrail 4B is a multimodal classifier built on Qwen/Qwen3.5‑4B. It detects safe versus unsafe visual content, with a focus on NSFW sensual material. The model is trained on the ImageShield‑Guardrail‑Pro dataset.
Good at
- Detecting NSFW sensual content
- Classifying safe vs unsafe images
- Analyzing dress codes and exposure
Limits
- Requires 8k context for memory estimates
- Experimental release, may generate unexpected behaviors
- Licensed under apache‑2.0
Best for
- Image moderation pipelines
- Content‑safety research
- Automated NSFW filtering
Who it’s for. Researchers and developers working on content‑safety solutions. The model is intended for research and content‑safety classification only; users must ensure safe, ethical, and lawful usage.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_S | 2.1 GB | 3.6 GB | Fits | Get file → | |
| Q3_K_M | 2.3 GB | 3.8 GB | Fits | Get file → | |
| Q3_K_L | 2.4 GB | 4.0 GB | Fits | Get file → | |
| Q4_0 | 2.5 GB | 4.1 GB | Fits | Get file → | |
| Q4_K_S | 2.6 GB | 4.1 GB | Fits | Get file → | |
| Q4_K_M | 2.7 GB | 4.3 GB | Fits | Get file → | |
| Q5_0 | 3.0 GB | 4.6 GB | Fits | Get file → | |
| Q5_K_S | 3.0 GB | 4.6 GB | Fits | Get file → | |
| Q5_K_M | 3.1 GB | 4.6 GB | Fits | Get file → | |
| BF16 | 8.4 GB | 10.0 GB | Too big | Get file → |
For 8GB VRAM, use Q4_K_M (est. 4.3GB at 8k context). For 6GB VRAM, use Q3_K_S (est. 3.6GB). For 4GB VRAM, use Q3_K_S or Q3_K_M if memory allows. BF16 requires 10GB memory and is not recommended for low‑budget setups.
What GPU do you need for VisionGuardrail 4B?
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: the best quant that fits is Q3_K_L (2.4 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q5_K_M (3.1 GB file, about 4.6 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_K_M (3.1 GB file, about 4.6 GB in use).
- 12 GB VRAM: the best quant that fits is BF16 (8.4 GB file, about 10.0 GB in use).
Which VisionGuardrail 4B quant should you choose?
Q4_K_M is the usual starting point for VisionGuardrail 4B: it balances file size and quality well. Here it is a 2.7 GB file.
If memory is tight, the smallest file is Q3_K_S at 2.1 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about VisionGuardrail 4B
How much VRAM does VisionGuardrail 4B need?
About 4.3 GB at Q4_K_M with an 8K context window. That is the 2.7 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 VisionGuardrail 4B on an 8 GB GPU?
Yes, with Q5_K_M: the 3.1 GB file needs about 4.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of VisionGuardrail 4B GGUF?
It depends on the quant: Q3_K_S is 2.1 GB, Q3_K_M is 2.3 GB, Q3_K_L is 2.4 GB, Q4_0 is 2.5 GB, Q4_K_S is 2.6 GB, Q4_K_M is 2.7 GB and 4 more.
What context length does VisionGuardrail 4B 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 VisionGuardrail 4B GGUF?
The files are on Hugging Face in the prithivMLmods/VisionGuardrail-4B-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 VisionGuardrail 4B 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 VisionGuardrail 4B on 8GB VRAM?
Yes, using Q4_K_M the model uses approximately 4.3GB at 8k context, which fits within 8GB VRAM.
What is the maximum context length supported?
The model was trained on 262144 tokens and can handle up to that context length.
Does the model support vision?
Yes, VisionGuardrail 4B is a multimodal model designed for visual content classification.