GP

Gpt Oss 120b

gpt-ossGGUF by DavidAUUpdated 2025-08-07
Download on Hugging Face
Parameters117B
Context128K
Layers36
Architecturegpt-oss
Smallest quant62.8 GB
Quick answer

Gpt Oss 120b needs about 63.9 GB of memory at MXFP4_MOE (a 62.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 2 quants, from 62.8 GB (MXFP4_MOE) to 65.9 GB (IQ4_NL). Longer context needs more: at 32K tokens the KV cache alone adds about 2.4 GB.

OpenAI GPT‑OSS 120B, 117B parameters, 5.1B active, for reasoning and coding

GPT‑OSS 120B is a 117B‑parameter model with 5.1B active parameters. It is trained on the harmony response format and supports chain‑of‑thought reasoning and function calling. The model is available in GGUF format with MXFP4_MOE and IQ4_NL quantizations.

Good at

  • Reasoning
  • Coding
  • Agentic function calling

Limits

  • Requires at least 8k context
  • Large VRAM requirement (≈64‑67 GB at 8k)
  • No vision support

Best for

  • Developers building reasoning agents
  • Fine‑tuning for custom workflows
  • Local inference on high‑memory GPUs

Who it’s for. Engineers and researchers needing a large, open‑weight model for complex reasoning tasks. The Apache‑2.0 license allows commercial use and customization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
MXFP4_MOE62.8 GB (4 parts) 63.9 GB
Too big Get file →
IQ4_NL65.9 GB (4 parts) 67.0 GB
Too big Get file →

For an 80 GB GPU, use the MXFP4_MOE quant (file size 62.81 GB, estimated 63.9 GB memory at 8k). If you have 64 GB or less, IQ4_NL (65.92 GB, 67 GB memory) is the next option. Both quants are tested and support 8k context.

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: 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 quant should you choose?

MXFP4_MOE (62.8 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 byDavidAU
Familygpt-oss
Licenseapache-2.0
Downloads (HF)1,367
Last updated2025-08-07

Frequently asked questions about Gpt Oss 120b

How much VRAM does Gpt Oss 120b need?

About 63.9 GB at MXFP4_MOE 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?

Not at an 8K context. The smallest file needs about 63.9 GB, so you would need a larger GPU or CPU offloading.

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

It depends on the quant: MXFP4_MOE is 62.8 GB, IQ4_NL is 65.9 GB.

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 DavidAU/Openai_gpt-oss-120b-NEO-Imatrix-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 this model on 8 GB VRAM?

No. The model requires around 64‑67 GB of VRAM at 8k context. Smaller GPUs cannot run it without significant offloading.

Does the model support vision?

No. The model only processes text and does not include vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license, allowing free use, modification, and commercial deployment.

Other GGUFs of gpt-oss-120b

Similar models

Browse all →

More from DavidAU

All by DavidAU →

More gpt-oss models

All gpt-oss →

Other large models

All large models →