GP

Gpt Oss 120b Derestricted

gpt-ossGGUF by gghfezUpdated 2025-11-30
Download on Hugging Face
Parameters117B
Context128K
Layers36
Architecturegpt-oss
Smallest quant63.4 GB
Quick answer

Gpt Oss 120b Derestricted needs about 64.5 GB of memory at MXFP4_MOE (a 63.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds. Longer context needs more: at 32K tokens the KV cache alone adds about 2.4 GB.

120 B‑parameter GPT‑OSS model with removed refusal behavior

Gpt Oss 120b Derestricted is a 120 B‑parameter GPT‑OSS model that has been modified to remove refusal behaviors while preserving reasoning performance. It uses Norm‑Preserving Biprojected Abliteration to keep weight norms intact. The model is released under Apache‑2.0 and supports a 131 072‑token context window.

Good at

  • High‑capacity reasoning
  • Large context handling
  • Uncensored responses

Limits

  • Requires ~64 GB VRAM for 8 k context
  • No vision or multimodal support
  • Apache‑2.0 license limits commercial use without attribution

Best for

  • Research on large‑scale language models
  • Creative writing without safety filters
  • Testing reasoning capabilities in unrestricted settings

Who it’s for. Developers and researchers who need a large, uncensored GPT‑OSS variant for experimentation. The model is suitable for academic or non‑commercial use under the Apache‑2.0 license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
MXFP4_MOE63.4 GB 64.5 GB
Too big Get file →

The available MXFP4_MOE quant is 63.39 GB and needs about 64.5 GB VRAM at 8 k context. For lower VRAM budgets, no other quant is provided, so the model cannot be run on less than 64 GB VRAM with the current quantization.

What GPU do you need for Gpt Oss 120b 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: 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: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: no quant fits at an 8K context.

Which Gpt Oss 120b Derestricted quant should you choose?

MXFP4_MOE (63.4 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegpt-oss
Parameters117B (approximate, mixture of experts)
Layers36
Trained context131,072 tokens
KV cache (fp16)72 KB per token

Source

Quantized bygghfez
Familygpt-oss
Licenseapache-2.0
Downloads (HF)8,097
Last updated2025-11-30

Frequently asked questions about Gpt Oss 120b Derestricted

How much VRAM does Gpt Oss 120b Derestricted need?

About 64.5 GB at MXFP4_MOE with an 8K context window. That is the 63.4 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 120b Derestricted on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 64.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Gpt Oss 120b Derestricted GGUF?

It depends on the quant: MXFP4_MOE is 63.4 GB.

What context length does Gpt Oss 120b 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 0.6 GB at 8K and 2.4 GB at 32K.

Where can I download Gpt Oss 120b Derestricted GGUF?

The files are on Hugging Face in the gghfez/gpt-oss-120b-Derestricted.MXFP4_MOE-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 120b 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 this model on 8 GB VRAM?

No. The MXFP4_MOE quant requires roughly 64 GB VRAM for 8 k context.

Does the model support vision or multimodal inputs?

No, it is a text‑only model.

What license applies to this model?

Apache‑2.0. Use is allowed for research and non‑commercial purposes with attribution.

Other GGUFs of gpt-oss-120b-Derestricted

Similar models

Browse all →

More from gghfez

All by gghfez →

More gpt-oss models

All gpt-oss →

Other large models

All large models →