GP

gpt-oss-20b-Derestricted

gpt-ossGGUF by MungertUpdated 2025-11-28
Download on Hugging Face
Parameters20.9B
Context128K
Layers24
Architecturegpt-oss
Smallest quant0.0 GB
Quick answer

gpt-oss-20b-Derestricted needs about 16.9 GB of memory at Q4_K_M (a 16.0 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 27 quants, from 0.0 GB to 41.9 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.

gpt-oss-20b-Derestricted – 20.9B‑parameter MoE model in GGUF format

The gpt-oss-20b-Derestricted model is a 20.9B‑parameter, mixture‑of‑experts language model. It is released under an Apache‑2.0 license and supports the harmony response format. The model is available in multiple GGUF quantizations.

Good at

  • Large‑context reasoning
  • Agentic function calling
  • Fine‑tuning

Limits

  • Requires 131072‑token context
  • No vision support
  • Large memory for high‑bit quantizations

Best for

  • Local inference on 16‑GB GPUs
  • Customizable reasoning pipelines
  • Developer experimentation

Who it’s for. Engineers and researchers who need a large, open‑weight model for reasoning and agentic tasks. The Apache‑2.0 license allows commercial use and modification.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 0.9 GB
Fits Get file →
IQ4_NL11.8 GB 12.7 GB
Too big Get file →
IQ1_S11.9 GB 12.8 GB
Too big Get file →
IQ2_XXS12.0 GB 12.9 GB
Too big Get file →
IQ1_M12.0 GB 12.9 GB
Too big Get file →
IQ2_XS12.0 GB 12.9 GB
Too big Get file →
Q2_K_M12.0 GB 12.9 GB
Too big Get file →
IQ2_M12.0 GB 12.9 GB
Too big Get file →
IQ2_S12.0 GB 12.9 GB
Too big Get file →
Q2_K_S12.0 GB 12.9 GB
Too big Get file →
Q3_K_S12.0 GB 12.9 GB
Too big Get file →
IQ3_XS12.4 GB 13.3 GB
Too big Get file →
IQ3_XXS12.4 GB 13.3 GB
Too big Get file →
IQ4_XS12.4 GB 13.3 GB
Too big Get file →
Q4_012.4 GB 13.3 GB
Too big Get file →
IQ3_M12.5 GB 13.4 GB
Too big Get file →
Q4_113.2 GB 14.1 GB
Too big Get file →
Q3_K_M13.2 GB 14.1 GB
Too big Get file →
Q5_014.9 GB 15.8 GB
Too big Get file →
Q4_K_S14.9 GB 15.8 GB
Too big Get file →
Q4_K_M16.0 GB 16.9 GB
Too big Get file →
Q5_116.1 GB 17.0 GB
Too big Get file →
Q5_K_M17.1 GB 18.0 GB
Too big Get file →
Q6_K_M22.2 GB 23.1 GB
Too big Get file →
Q8_022.3 GB 23.2 GB
Too big Get file →
F1623.6 GB 24.5 GB
Too big Get file →
BF1641.9 GB 42.8 GB
Too big Get file →

For 8‑GB VRAM, use IQ4_NL (12.7 GB memory at 8k context). For 16‑GB VRAM, Q4_K_M (16.9 GB memory) or Q5_0 (15.8 GB memory) are suitable. For 32‑GB VRAM, Q6_K_M (23.1 GB memory) or Q8_0 (23.2 GB memory) provide higher precision.

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

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 (14.9 GB file, about 15.8 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (22.3 GB file, about 23.2 GB in use).
  • 32 GB VRAM: the best quant that fits is F16 (23.6 GB file, about 24.5 GB in use).
  • 48 GB VRAM: the best quant that fits is BF16 (41.9 GB file, about 42.8 GB in use).

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

Q4_K_M is the usual starting point for gpt-oss-20b-Derestricted: it balances file size and quality well. Here it is a 16.0 GB file.

The Q8_0 file is 22.3 GB, about 1.4 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)683
Last updated2025-11-28

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

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

About 16.9 GB at Q4_K_M with an 8K context window. That is the 16.0 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-20b-Derestricted 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-20b-Derestricted GGUF?

It depends on the quant: file is 0.0 GB, IQ4_NL is 11.8 GB, IQ1_S is 11.9 GB, IQ2_XXS is 12.0 GB, IQ1_M is 12.0 GB, IQ2_XS is 12.0 GB and 21 more.

What context length does gpt-oss-20b-Derestricted 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-20b-Derestricted GGUF?

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

Use the IQ4_NL quantization; it requires about 12.7 GB memory at 8k context, which is close to 8 GB but may need CPU fallback.

Does this model support vision tasks?

No, the model has no vision capabilities.

What license does the model use?

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 →