GP

gpt-oss-safeguard-20b

gpt-ossGGUF by MungertUpdated 2025-10-31
Download on Hugging Face
Parameters20.9B
Context128K
Layers24
Architecturegpt-oss
Smallest quant0.0 GB
Quick answer

gpt-oss-safeguard-20b needs about 12.8 GB of memory at Q4_K_M (a 11.9 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 27 quants, from 0.0 GB to 13.8 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.

gpt-oss-safeguard-20b – 20.9B‑parameter safety reasoning model

gpt-oss-safeguard-20b is a 20.9B‑parameter GPT‑OSS model fine‑tuned for safety reasoning. It supports function calling and structured outputs. The model is released under Apache‑2.0 and is compatible with the harmony response format.

Good at

  • Safety content classification
  • Policy‑driven filtering
  • Structured safety outputs

Limits

  • Requires harmony format
  • No vision support
  • Large memory for high context

Best for

  • LLM input‑output filtering
  • Online content labeling
  • Offline trust and safety labeling

Who it’s for. Developers building safety‑aware LLM applications. The model is suitable for local deployment on GPUs with 16GB VRAM and for use cases that need policy‑driven content moderation.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 0.9 GB
Fits Get file →
IQ4_NL11.2 GB 12.1 GB
Too big Get file →
IQ1_S11.3 GB 12.2 GB
Too big Get file →
Q2_K_S11.3 GB 12.2 GB
Too big Get file →
IQ2_XXS11.4 GB 12.3 GB
Too big Get file →
IQ1_M11.4 GB 12.3 GB
Too big Get file →
IQ2_XS11.4 GB 12.3 GB
Too big Get file →
Q2_K_M11.4 GB 12.3 GB
Too big Get file →
IQ2_M11.4 GB 12.3 GB
Too big Get file →
IQ2_S11.4 GB 12.3 GB
Too big Get file →
Q4_111.4 GB 12.3 GB
Too big Get file →
Q3_K_S11.4 GB 12.3 GB
Too big Get file →
IQ3_XS11.8 GB 12.7 GB
Too big Get file →
IQ3_XXS11.8 GB 12.7 GB
Too big Get file →
IQ3_M11.8 GB 12.7 GB
Too big Get file →
IQ4_XS11.8 GB 12.7 GB
Too big Get file →
Q3_K_M11.8 GB 12.7 GB
Too big Get file →
Q4_011.8 GB 12.7 GB
Too big Get file →
Q4_K_S11.8 GB 12.7 GB
Too big Get file →
Q4_K_M11.9 GB 12.8 GB
Too big Get file →
Q5_011.9 GB 12.8 GB
Too big Get file →
Q5_K_M11.9 GB 12.8 GB
Too big Get file →
Q5_111.9 GB 12.8 GB
Too big Get file →
Q6_K_M12.0 GB 12.9 GB
Too big Get file →
Q8_012.1 GB 13.0 GB
Too big Get file →
F1613.5 GB 14.4 GB
Too big Get file →
BF1613.8 GB 14.7 GB
Too big Get file →

For 8GB VRAM use the IQ4_NL quant (file size 11.22GB, memory 12.1GB). For 12GB VRAM use Q4_0 (file size 11.79GB, memory 12.7GB). For 16GB VRAM use Q5_0 (file size 11.87GB, memory 12.8GB). Estimates are approximate.

What GPU do you need for gpt-oss-safeguard-20b?

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 the main file (0.0 GB file, about 0.9 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.9 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.9 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.9 GB in use).
  • 16 GB VRAM: the best quant that fits is BF16 (13.8 GB file, about 14.7 GB in use).

Which gpt-oss-safeguard-20b quant should you choose?

Q4_K_M is the usual starting point for gpt-oss-safeguard-20b: it balances file size and quality well. Here it is a 11.9 GB file.

The Q8_0 file is 12.1 GB, about 1.0 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 the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegpt-oss
Parameters20.9B (approximate, mixture of experts)
Layers24
Trained context131,072 tokens
KV cache (fp16)48 KB per token

Source

Quantized byMungert
Familygpt-oss
Licenseapache-2.0
Downloads (HF)272
Last updated2025-10-31

Frequently asked questions about gpt-oss-safeguard-20b

How much VRAM does gpt-oss-safeguard-20b need?

About 12.8 GB at Q4_K_M with an 8K context window. That is the 11.9 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 gpt-oss-safeguard-20b on an 8 GB GPU?

Yes, with the smaller files: the 0.0 GB file needs about 0.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of gpt-oss-safeguard-20b GGUF?

It depends on the quant: file is 0.0 GB, IQ4_NL is 11.2 GB, IQ1_S is 11.3 GB, Q2_K_S is 11.3 GB, IQ2_XXS is 11.4 GB, IQ1_M is 11.4 GB and 21 more.

What context length does gpt-oss-safeguard-20b support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.6 GB at 32K.

Where can I download gpt-oss-safeguard-20b GGUF?

The files are on Hugging Face in the Mungert/gpt-oss-safeguard-20b-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 gpt-oss-safeguard-20b 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 gpt-oss-safeguard-20b on 8GB VRAM?

Use the IQ4_NL quant; it requires about 12.1GB of VRAM at 8k context, so 8GB VRAM is insufficient.

Does the model support image inputs?

No, the model has no vision capability.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of gpt-oss-20b

Similar models

Browse all →

More from Mungert

All by Mungert →

More gpt-oss models

All gpt-oss →

Other medium models

All medium models →