ON

OneDecision VisionGuard 4B SFT

OnedecisionGGUF by prithivMLmodsUpdated 2026-10-07
Download on Hugging Face
Parameters4.21B
Context256K
Layers32
Architectureqwen35
Smallest quant2.3 GB
Quick answer

OneDecision VisionGuard 4B SFT 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 8 quants, from 2.3 GB (Q3_K_M) to 8.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Dense 4‑B multimodal model for Safe/NSFW image classification

OneDecision VisionGuard 4B SFT is a 4.21‑billion‑parameter multimodal model based on Qwen/Qwen3.5‑4B. 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

  • Safe/NSFW image classification
  • Detailed dress‑code and pose analysis
  • Conservative safety policy

Limits

  • No vision support beyond image classification
  • Large context requires 262144 tokens
  • Apache‑2.0 license restricts commercial use

Best for

  • Content‑safety moderation
  • Image classification pipelines
  • Research on visual guardrails

Who it’s for. Developers building content‑safety systems or researchers studying multimodal classification. The model is intended for research and content‑safety classification only.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M2.3 GB 3.8 GB
Fits Get file →
Q3_K_L2.4 GB 4.0 GB
Fits Get file →
Q4_K_S2.6 GB 4.1 GB
Fits Get file →
Q4_K_M2.7 GB 4.3 GB
Fits Get file →
Q5_K_S3.0 GB 4.6 GB
Fits Get file →
Q5_K_M3.1 GB 4.6 GB
Fits Get file →
Q6_K3.5 GB 5.0 GB
Fits Get file →
BF168.4 GB 10.0 GB
Too big Get file →

For 8 GB VRAM, use Q3_K_M (file size 2.26 GB, estimated 3.8 GB memory at 8 k context). If more memory is available, Q4_K_M (2.71 GB, 4.3 GB) or Q5_K_M (3.07 GB, 4.6 GB) provide higher precision. BF16 requires 10 GB memory and is not recommended for limited VRAM.

What GPU do you need for OneDecision VisionGuard 4B 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: 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 Q6_K (3.5 GB file, about 5.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (3.5 GB file, about 5.0 GB in use).
  • 12 GB VRAM: the best quant that fits is BF16 (8.4 GB file, about 10.0 GB in use).

Which OneDecision VisionGuard 4B SFT quant should you choose?

Q4_K_M is the usual starting point for OneDecision VisionGuard 4B SFT: 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_M at 2.3 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

Architectureqwen35
Parameters4.21B
Layers32
Trained context262,144 tokens
KV cache (fp16)128 KB per token

Source

Quantized byprithivMLmods
Licenseapache-2.0
Downloads (HF)1,808
Last updated2026-10-07

Frequently asked questions about OneDecision VisionGuard 4B SFT

How much VRAM does OneDecision VisionGuard 4B SFT 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 OneDecision VisionGuard 4B SFT on an 8 GB GPU?

Yes, with Q6_K: the 3.5 GB file needs about 5.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of OneDecision VisionGuard 4B SFT GGUF?

It depends on the quant: Q3_K_M is 2.3 GB, Q3_K_L is 2.4 GB, Q4_K_S is 2.6 GB, Q4_K_M is 2.7 GB, Q5_K_S is 3.0 GB, Q5_K_M is 3.1 GB and 2 more.

What context length does OneDecision VisionGuard 4B 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 4B SFT GGUF?

The files are on Hugging Face in the prithivMLmods/OneDecision-VisionGuard-4B-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 4B 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 Q3_K_M quantized file uses approximately 3.8 GB memory at 8 k context, fitting within 8 GB VRAM.

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.

Other GGUFs of OneDecision-VisionGuard-4B-SFT

Similar models

Browse all →

More from prithivMLmods

All by prithivMLmods →

More Onedecision models

All Onedecision →

Other small models

All small models →