gpt-oss-120b-VISION-v2 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-VISION-v2 in GGUF format
gpt-oss-120b-VISION-v2 is a 117B‑parameter GPT‑OSS model with vision, reasoning, and tool use. It is quantized with MXFP4 and available as a single GGUF file. The model supports a 131072‑token context and is licensed under Apache 2.0.
Good at
- Vision and image understanding
- Reasoning with chain‑of‑thought
- Tool calling and function execution
Limits
- Requires ~66.5 GB VRAM at 8 k context
- No native vision support in llama.cpp
- Only one quantization available (MXFP4)
Best for
- Vision‑enabled chat agents
- Complex reasoning workflows
- Custom fine‑tuning for specific domains
Who it’s for. Developers building agentic applications that need vision, reasoning, and tool use. The model is suitable for research, experimentation, and commercial deployment under the permissive Apache 2.0 license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| MXFP4 | 65.4 GB (2 parts) | 66.5 GB | Too big | Get file → |
The only available quant is MXFP4, 65.37 GB on disk and ~66.5 GB VRAM at 8 k context. It fits on a single 80 GB GPU such as NVIDIA H100 or AMD MI300X. For lower VRAM budgets the model is not supported.
What GPU do you need for gpt-oss-120b-VISION-v2?
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-VISION-v2 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-VISION-v2
How much VRAM does gpt-oss-120b-VISION-v2 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-VISION-v2 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-VISION-v2 GGUF?
It depends on the quant: MXFP4 is 65.4 GB.
What context length does gpt-oss-120b-VISION-v2 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-VISION-v2 GGUF?
The files are on Hugging Face in the SoAIHQ/gpt-oss-120b-VISION-v2-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-VISION-v2 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-VISION-v2 on 8 GB VRAM?
No, the MXFP4 quant requires about 66.5 GB VRAM at 8 k context, so 8 GB is insufficient.
Does this model support vision?
Yes, it includes image input capabilities as part of the gpt‑oss‑120b‑VISION‑v2 release.
What license does it use?
The model is released under the Apache 2.0 license, allowing free use and modification.