ON

OneDecision VisionGuard 4B SFT

OnedecisionGGUF by mradermacherUpdated 2026-10-07
Download on Hugging Face
Parameters4.21B
Context256K
Layers32
Architectureqwen35
Smallest quant1.9 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 12 quants, from 1.9 GB (Q2_K) to 8.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

4‑Billion‑parameter multimodal image safety classifier

OneDecision VisionGuard 4B SFT is a dense 4‑billion‑parameter model built on Qwen/Qwen3.5‑4B. It classifies images as Safe or NSFW, focusing on sensual and other sensitive content. The model outputs structured JSON with scene description, classification, and reasoning.

Good at

  • Image safety classification
  • NSFW sensual content detection
  • Dress‑code and pose analysis

Limits

  • No vision support beyond image classification
  • Requires 8k context for full performance
  • Apache‑2.0 license limits commercial use

Best for

  • Content‑moderation pipelines
  • Image‑based safety checks
  • Automated NSFW filtering

Who it’s for. Researchers and developers needing a lightweight, open‑source image safety model. The model is suitable for integration into moderation systems where structured JSON output is required.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.9 GB 3.5 GB
Fits Get file →
Q3_K_S2.1 GB 3.6 GB
Fits Get file →
Q3_K_M2.3 GB 3.8 GB
Fits Get file →
Q3_K_L2.4 GB 4.0 GB
Fits Get file →
IQ4_XS2.5 GB 4.1 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 →
Q8_04.5 GB 6.1 GB
Fits Get file →
F168.4 GB 10.0 GB
Too big Get file →

For 8 GB VRAM use Q4_K_S (2.56 GB, 4.1 GB memory at 8k). For 4 GB VRAM use Q2_K (1.92 GB, 3.5 GB memory). For 16 GB VRAM use Q5_K_M (3.07 GB, 4.6 GB memory). Estimates are approximate.

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 Q8_0 (4.5 GB file, about 6.1 GB in use).
  • 12 GB VRAM: the best quant that fits is F16 (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.

The Q8_0 file is 4.5 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 1.9 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

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

Source

Quantized bymradermacher
Licenseapache-2.0
Downloads (HF)1,238
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 Q8_0: the 4.5 GB file needs about 6.1 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: Q2_K is 1.9 GB, Q3_K_S is 2.1 GB, Q3_K_M is 2.3 GB, Q3_K_L is 2.4 GB, IQ4_XS is 2.5 GB, Q4_K_S is 2.6 GB and 6 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 mradermacher/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 OneDecision VisionGuard 4B SFT on 8 GB VRAM?

Yes, the Q4_K_S quant uses 2.56 GB file size and requires about 4.1 GB VRAM at 8k context.

Does the model support text generation?

No, it is a multimodal image classification model only.

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 mradermacher

All by mradermacher →

More Onedecision models

All Onedecision →

Other small models

All small models →