GP

gpt oss 120b ultra heretic

gpt-ossGGUF by llmfan46Updated 2026-05-25
Download on Hugging Face
Parameters117B
Context128K
Layers36
Architecturegpt-oss
Smallest quant65.4 GB
Quick answer

gpt oss 120b ultra heretic needs about 66.5 GB of memory at MXFP4 (a 65.4 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.

Open-weight GPT‑OSS 120B model with high reasoning and chain‑of‑thought

gpt‑oss‑120b‑ultra‑heretic is a 117B‑parameter model released under Apache‑2.0. It supports 131072‑token context and is designed for powerful reasoning and agentic tasks. The model is available in a single MXFP4 quantization.

Good at

  • Powerful reasoning
  • Chain‑of‑thought debugging
  • Agentic task execution

Limits

  • Requires ~66.5 GB VRAM at 8k context
  • Large context length limits local deployment
  • No vision support

Best for

  • High‑reasoning applications
  • Agentic workflow design
  • Debugging chain‑of‑thought outputs

Who it’s for. Developers and researchers who need an open‑weight, high‑capacity language model for complex reasoning tasks and want to customize or fine‑tune the model under a permissive license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
MXFP465.4 GB 66.5 GB
Too big Get file →

The only available quant is MXFP4, 65.37 GB file size. It requires approximately 66.5 GB VRAM at 8k context. For 80 GB GPUs this is the recommended configuration. No other quantizations are provided.

What GPU do you need for gpt oss 120b ultra heretic?

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 ultra heretic quant should you choose?

MXFP4 (65.4 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 byllmfan46
Familygpt-oss
Licenseapache-2.0
Downloads (HF)1,317
Last updated2026-05-25

Frequently asked questions about gpt oss 120b ultra heretic

How much VRAM does gpt oss 120b ultra heretic need?

About 66.5 GB at MXFP4 with an 8K context window. That is the 65.4 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 ultra heretic on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 66.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of gpt oss 120b ultra heretic GGUF?

It depends on the quant: MXFP4 is 65.4 GB.

What context length does gpt oss 120b ultra heretic 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 ultra heretic GGUF?

The files are on Hugging Face in the llmfan46/gpt-oss-120b-ultra-heretic-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 ultra heretic 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 quantization requires about 66.5 GB VRAM at 8k context, which far exceeds 8 GB.

Can I use this model with llama.cpp?

Yes, the model is compatible with llama.cpp, LM Studio, Ollama, and other GGUF‑compatible tools.

Is the model fine‑tunable?

Yes, the model is fully fine‑tunable for specific use cases.

Similar models

Browse all →

More from llmfan46

All by llmfan46 →

More gpt-oss models

All gpt-oss →

Other large models

All large models →