Openai_Gpt Oss 120b needs about 64.5 GB of memory at MXFP4 (a 63.4 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, 120 B parameters, MXFP4 quantized for 80 GB GPU
OpenAI GPT‑OSS 120B is a 120 B‑parameter model with 5.1 B active parameters. It is quantized with MXFP4, enabling inference on a single 80 GB GPU such as NVIDIA H100 or AMD MI300X. The model supports full chain‑of‑thought reasoning and agentic tasks like function calling and code execution.
Good at
- High‑reasoning tasks
- Agentic function calling
- Chain‑of‑thought debugging
Limits
- Requires 80 GB VRAM for MXFP4
- No vision support
- Apache 2.0 license only
Best for
- Enterprise reasoning workloads
- Customizable agentic pipelines
- Debug‑heavy research projects
Who it’s for. Developers and enterprises needing large‑scale reasoning and agentic capabilities on powerful GPUs. The model is suitable for production workloads that can accommodate the 80 GB VRAM requirement.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| MXFP4 | 63.4 GB (2 parts) | 64.5 GB | Too big | Get file → |
The MXFP4 quantized file is 63.39 GB and needs about 64.5 GB VRAM at 8 k context. For 80 GB GPUs, this is the recommended quant. No other quants are available, so use MXFP4 for best performance within the memory budget.
What GPU do you need for Openai_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 Openai_Gpt Oss 120b quant should you choose?
MXFP4 (63.4 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 Openai_Gpt Oss 120b
How much VRAM does Openai_Gpt Oss 120b need?
About 64.5 GB at MXFP4 with an 8K context window. That is the 63.4 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 Openai_Gpt Oss 120b on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 64.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Openai_Gpt Oss 120b GGUF?
It depends on the quant: MXFP4 is 63.4 GB.
What context length does Openai_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 Openai_Gpt Oss 120b GGUF?
The files are on Hugging Face in the lmstudio-community/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 Openai_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 MXFP4 quantized model requires roughly 64.5 GB VRAM at 8 k context, far exceeding 8 GB.
What license does this model use?
Apache 2.0, allowing free use, modification, and commercial deployment without copyleft.
Does the model support vision tasks?
No, it is a text‑only model and does not include vision capabilities.