ON

OneDecision VisionGuard 27B SFT

OnedecisionGGUF by prithivMLmodsUpdated 2026-10-07
Download on Hugging Face
Parameters26.9B
Context256K
Layers64
Architectureqwen35
Smallest quant13.3 GB
Quick answer

OneDecision VisionGuard 27B SFT needs about 19.2 GB of memory at Q4_K_M (a 16.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 4 quants, from 13.3 GB (Q3_K_M) to 53.8 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

Dense 27B multimodal image safety classifier

OneDecision VisionGuard 27B SFT is a dense 27‑billion‑parameter multimodal model based on Qwen/Qwen3.8‑27B. 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

  • Safe/NSFW image classification
  • Detailed dress‑code and pose analysis
  • Structured JSON output

Limits

  • No vision support in llama.cpp
  • Requires large VRAM for full precision
  • Apache‑2.0 license limits commercial use

Best for

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

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

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M13.3 GB 15.9 GB
Too big Get file →
Q4_K_M16.5 GB 19.2 GB
Too big Get file →
Q5_K_M19.2 GB 21.9 GB
Too big Get file →
BF1653.8 GB 56.5 GB
Too big Get file →

For 8 GB VRAM use Q3_K_M (13.3 GB file, ~15.9 GB memory). For 12 GB VRAM use Q4_K_M (16.55 GB file, ~19.2 GB memory). For 16 GB VRAM use Q5_K_M (19.23 GB file, ~21.9 GB memory). Full precision BF16 requires 53.81 GB file and ~56.5 GB memory.

What GPU do you need for OneDecision VisionGuard 27B 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: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is Q3_K_M (13.3 GB file, about 15.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_K_M (19.2 GB file, about 21.9 GB in use).
  • 32 GB VRAM: the best quant that fits is Q5_K_M (19.2 GB file, about 21.9 GB in use).
  • 48 GB VRAM: the best quant that fits is Q5_K_M (19.2 GB file, about 21.9 GB in use).

Which OneDecision VisionGuard 27B SFT quant should you choose?

Q4_K_M is the usual starting point for OneDecision VisionGuard 27B SFT: it balances file size and quality well. Here it is a 16.5 GB file.

If memory is tight, the smallest file is Q3_K_M at 13.3 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
Parameters26.9B
Layers64
Trained context262,144 tokens
KV cache (fp16)256 KB per token

Source

Quantized byprithivMLmods
Licenseapache-2.0
Downloads (HF)1,110
Last updated2026-10-07

Frequently asked questions about OneDecision VisionGuard 27B SFT

How much VRAM does OneDecision VisionGuard 27B SFT need?

About 19.2 GB at Q4_K_M with an 8K context window. That is the 16.5 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 27B SFT on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of OneDecision VisionGuard 27B SFT GGUF?

It depends on the quant: Q3_K_M is 13.3 GB, Q4_K_M is 16.5 GB, Q5_K_M is 19.2 GB, BF16 is 53.8 GB.

What context length does OneDecision VisionGuard 27B 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 2.1 GB at 8K and 8.6 GB at 32K.

Where can I download OneDecision VisionGuard 27B SFT GGUF?

The files are on Hugging Face in the prithivMLmods/OneDecision-VisionGuard-27B-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 27B 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 27B SFT on 8 GB VRAM?

Use the Q3_K_M quantized file. It requires 13.3 GB file size and approximately 15.9 GB VRAM at 8k context.

Does the model support vision in llama.cpp?

No, the model is not supported for vision in llama.cpp. Use the Transformers setup for full functionality.

What license applies to this model?

The model is released under the apache-2.0 license.

Other GGUFs of OneDecision-VisionGuard-27B-SFT

Similar models

Browse all →

More from prithivMLmods

All by prithivMLmods →

More Onedecision models

All Onedecision →

Other medium models

All medium models →