GP

Gpt Oss Safeguard 20b Kor Enterprise

gpt-ossGGUF by mradermacherUpdated 2025-12-04
Download on Hugging Face
Parameters20.9B
Context128K
Layers24
Architecturegpt-oss
Smallest quant0.0 GB
Quick answer

Gpt Oss Safeguard 20b Kor Enterprise needs about 16.7 GB of memory at Q4_K_M (a 15.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 25 quants, from 0.0 GB to 22.2 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.

20B Korean enterprise LLM fine‑tuned from gpt‑oss‑20b

Gpt Oss Safeguard 20b Kor Enterprise is a 20.9B‑parameter Korean‑focused LLM. It is fine‑tuned on 2.74M Korean corporate, legal, and public domain documents. The model supports tools and runs in GGUF format.

Good at

  • Korean business document generation
  • K‑IFRS and legal text summarization
  • Table and CSV data conversion

Limits

  • No vision support
  • Requires large VRAM for full precision
  • Apache‑2.0 license limits commercial redistribution

Best for

  • Automated Korean corporate memos
  • K‑IFRS report drafting
  • Legal clause extraction

Who it’s for. Developers building Korean enterprise applications that need accurate business and legal language. It is suitable for internal tools that generate or summarize Korean corporate documents.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 0.9 GB
Fits Get file →
IQ1_M12.0 GB 12.9 GB
Too big Get file →
IQ1_S12.0 GB 12.9 GB
Too big Get file →
IQ2_XXS12.0 GB 12.9 GB
Too big Get file →
IQ2_XS12.0 GB 12.9 GB
Too big Get file →
Q3_K_S12.1 GB 13.0 GB
Too big Get file →
IQ2_M12.1 GB 13.0 GB
Too big Get file →
IQ2_S12.1 GB 13.0 GB
Too big Get file →
IQ3_S12.1 GB 13.0 GB
Too big Get file →
IQ3_XS12.1 GB 13.0 GB
Too big Get file →
IQ3_XXS12.1 GB 13.0 GB
Too big Get file →
Q2_K12.1 GB 13.0 GB
Too big Get file →
IQ4_XS12.1 GB 13.0 GB
Too big Get file →
MXFP4_MOE12.1 GB 13.0 GB
Too big Get file →
Q2_K_S12.1 GB 13.0 GB
Too big Get file →
Q4_012.1 GB 13.1 GB
Too big Get file →
IQ3_M12.2 GB 13.1 GB
Too big Get file →
Q3_K_M12.9 GB 13.8 GB
Too big Get file →
Q3_K_L13.3 GB 14.2 GB
Too big Get file →
Q4_113.4 GB 14.3 GB
Too big Get file →
Q4_K_S14.7 GB 15.6 GB
Too big Get file →
Q4_K_M15.8 GB 16.7 GB
Too big Get file →
Q5_K_S15.9 GB 16.8 GB
Too big Get file →
Q5_K_M16.9 GB 17.8 GB
Too big Get file →
Q6_K22.2 GB 23.1 GB
Too big Get file →

For 8 GB VRAM use Q4_K_M (15.81 GB file, ~16.7 GB memory). For 12 GB VRAM use Q3_K_M (12.92 GB file, ~13.8 GB memory). For 16 GB VRAM use Q5_K_M (16.89 GB file, ~17.8 GB memory).

What GPU do you need for Gpt Oss Safeguard 20b Kor Enterprise?

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 Q4_K_S (14.7 GB file, about 15.6 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (22.2 GB file, about 23.1 GB in use).

Which Gpt Oss Safeguard 20b Kor Enterprise quant should you choose?

Q4_K_M is the usual starting point for Gpt Oss Safeguard 20b Kor Enterprise: it balances file size and quality well. Here it is a 15.8 GB file.

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 bymradermacher
Familygpt-oss
Licenseapache-2.0
Downloads (HF)676
Last updated2025-12-04

Frequently asked questions about Gpt Oss Safeguard 20b Kor Enterprise

How much VRAM does Gpt Oss Safeguard 20b Kor Enterprise need?

About 16.7 GB at Q4_K_M with an 8K context window. That is the 15.8 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 Kor Enterprise 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 Kor Enterprise GGUF?

It depends on the quant: file is 0.0 GB, IQ1_M is 12.0 GB, IQ1_S is 12.0 GB, IQ2_XXS is 12.0 GB, IQ2_XS is 12.0 GB, Q3_K_S is 12.1 GB and 19 more.

What context length does Gpt Oss Safeguard 20b Kor Enterprise 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 Kor Enterprise GGUF?

The files are on Hugging Face in the mradermacher/gpt-oss-safeguard-20b-kor-enterprise-i1-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 Kor Enterprise 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, using the Q4_K_M quant which requires about 16.7 GB of VRAM at 8k context.

Does this model support image input?

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-safeguard-20b-kor-enterprise

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More gpt-oss models

All gpt-oss →

Other medium models

All medium models →