GP

Gpt Oss 120b

gpt-ossGGUF by bartowskiUpdated 2025-08-11
Download on Hugging Face
Parameters117B
Context128K
Layers36
Architecturegpt-oss
Smallest quant0.2 GB
Quick answer

Gpt Oss 120b needs about 63.9 GB of memory at Q4_K_M (a 62.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 19 quants, from 0.2 GB to 65.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.4 GB.

120‑billion‑parameter GPT‑OSS model for high‑reasoning tasks

Gpt Oss 120b is a 120 billion‑parameter GPT‑OSS model trained on the harmony response format. It supports chain‑of‑thought reasoning, function calling, web browsing, Python execution, and structured outputs. The model is licensed under Apache‑2.0 and can be fine‑tuned.

Good at

  • High‑reasoning tasks
  • Agentic function calling
  • Chain‑of‑thought debugging

Limits

  • Requires 80 GB GPU for full precision
  • No vision support
  • Large context length of 131 072 tokens

Best for

  • Enterprise reasoning workflows
  • Custom agent development
  • Debugging complex prompts

Who it’s for. Developers and researchers needing a large, open‑weight model for reasoning and agentic tasks. The model is suitable for production use on high‑end GPUs and for fine‑tuning to specialized domains.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.2 GB 1.3 GB
Fits Get file →
Q3_K_L62.6 GB (2 parts) 63.7 GB
Too big Get file →
Q4_062.6 GB (2 parts) 63.8 GB
Too big Get file →
IQ2_M62.7 GB (2 parts) 63.8 GB
Too big Get file →
Q3_K_S62.7 GB (2 parts) 63.8 GB
Too big Get file →
IQ3_M62.7 GB (2 parts) 63.8 GB
Too big Get file →
Q2_K62.7 GB (2 parts) 63.8 GB
Too big Get file →
Q3_K_M62.7 GB (2 parts) 63.8 GB
Too big Get file →
IQ4_NL62.7 GB (2 parts) 63.8 GB
Too big Get file →
IQ4_XS62.7 GB (2 parts) 63.8 GB
Too big Get file →
Q4_162.7 GB (2 parts) 63.8 GB
Too big Get file →
Q4_K_M62.8 GB (2 parts) 63.9 GB
Too big Get file →
Q3_K_XL62.9 GB (2 parts) 64.0 GB
Too big Get file →
Q2_K_L63.0 GB (2 parts) 64.1 GB
Too big Get file →
Q4_K_L63.1 GB (2 parts) 64.2 GB
Too big Get file →
Q6_K63.3 GB (2 parts) 64.4 GB
Too big Get file →
Q8_063.4 GB (2 parts) 64.5 GB
Too big Get file →
MXFP4_MOE63.4 GB (2 parts) 64.5 GB
Too big Get file →
BF1665.4 GB (2 parts) 66.5 GB
Too big Get file →

For 80 GB GPUs, use the MXFP4 quantization (63.39 GB) or BF16 (65.37 GB). If memory is limited, Q4_0 (62.65 GB) or Q3_K_L (62.6 GB) provide a good trade‑off. Smaller quants like Q3_K_S or IQ2_M are available but offer little size savings.

What GPU do you need for Gpt Oss 120b?

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 (0.2 GB file, about 1.3 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 1.3 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 1.3 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 1.3 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 1.3 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 1.3 GB in use).
  • 32 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 1.3 GB in use).
  • 48 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 1.3 GB in use).

Which Gpt Oss 120b quant should you choose?

Q4_K_M is the usual starting point for Gpt Oss 120b: it balances file size and quality well. Here it is a 62.8 GB file.

The Q8_0 file is 63.4 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 0.2 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
Parameters117B (approximate, mixture of experts)
Layers36
Trained context131,072 tokens
KV cache (fp16)72 KB per token

Source

Quantized bybartowski
Familygpt-oss
Licenseapache-2.0
Downloads (HF)3,665
Last updated2025-08-11

Frequently asked questions about Gpt Oss 120b

How much VRAM does Gpt Oss 120b need?

About 63.9 GB at Q4_K_M with an 8K context window. That is the 62.8 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 120b on an 8 GB GPU?

Yes, with the smaller files: the 0.2 GB file needs about 1.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

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

It depends on the quant: file is 0.2 GB, Q3_K_L is 62.6 GB, Q4_0 is 62.6 GB, IQ2_M is 62.7 GB, Q3_K_S is 62.7 GB, IQ3_M is 62.7 GB and 13 more.

What context length does Gpt Oss 120b 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 GGUF?

The files are on Hugging Face in the bartowski/openai_gpt-oss-120b-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 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 120b on a single 80GB GPU?

Yes, the MXFP4 quantization is designed for a single 80GB GPU such as NVIDIA H100 or AMD MI300X.

What is the context length of this model?

The model supports up to 131,072 tokens in context.

Is there a vision capability?

No, the model does not support vision inputs.

Other GGUFs of gpt-oss-120b

Similar models

Browse all →

More from bartowski

All by bartowski →

More gpt-oss models

All gpt-oss →

Other large models

All large models →