Gpt Oss 120b 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.
OpenAI GPT‑OSS 120B with vision, 117B parameters, MXFP4 quantized
GPT‑OSS 120B is an open‑weight model with 117B parameters and 131072 trained context tokens. It supports tools and vision, and is released under Apache‑2.0. The model is quantized to MXFP4, enabling inference on a single 80GB GPU.
Good at
- Reasoning and agentic tasks
- Vision input via mmproj add‑on
- Tool calling and structured outputs
Limits
- Requires 80GB GPU for MXFP4 build
- Only works with harmony prompt format
- No other quantizations available
Best for
- High‑reasoning chat applications
- Vision‑enabled agentic workflows
- Fine‑tuning for custom tasks
Who it’s for. Developers needing a large, open‑weight reasoning model with vision support. Suitable for research, experimentation, and commercial deployment under Apache‑2.0.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| MXFP4 | 65.4 GB (2 parts) | 66.5 GB | Too big | Get file → |
The MXFP4 build is 65.37 GB and needs about 66.5 GB of VRAM at 8K context. It is split into two shards. For 80GB GPUs, this is the recommended quant. No other quantizations are provided.
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 (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
Source
Frequently asked questions about Gpt Oss 120b
How much VRAM does Gpt Oss 120b 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 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 GGUF?
It depends on the quant: MXFP4 is 65.4 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 SoAIHQ/gpt-oss-120b-VISION-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 8GB VRAM?
No. The MXFP4 build requires 66.5 GB VRAM at 8K context, so 8GB is insufficient.
Does the model support vision?
Yes, it supports vision with the mmproj‑gpt‑oss‑120b‑f16.gguf add‑on.
What license does it use?
Apache‑2.0, allowing free use, modification, and commercial deployment.