gpt-oss-120b needs about 2.1 GB of memory at BF16 (a 1.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 0.8 GB (Q8_0) to 63.4 GB (MXFP4). Longer context needs more: at 32K tokens the KV cache alone adds about 0.1 GB.
gpt-oss-120b – 117B parameter GPT model with full chain‑of‑thought and function calling
gpt-oss-120b is a 117B parameter model from the gpt‑oss family, built on the eagle3 architecture. It supports tools, chain‑of‑thought reasoning, and agentic tasks such as function calling and web browsing. The model is released under an Apache‑2.0 license.
Good at
- Reasoning and chain‑of‑thought
- Function calling and web browsing
- Agentic task execution
Limits
- No vision support
- Requires 8k context for memory estimates
- Large VRAM needed for full precision
Best for
- Enterprise reasoning workflows
- Developer tool integration
- Custom fine‑tuning projects
Who it’s for. This model is suited for developers and enterprises that need powerful reasoning and agentic capabilities in a single GPU setup. It is ideal for applications requiring full chain‑of‑thought and function calling without copyleft restrictions.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 0.8 GB | 1.4 GB | Fits | Get file → | |
| BF16 | 1.6 GB | 2.1 GB | Fits | Get file → | |
| MXFP4 | 63.4 GB | 63.9 GB | Too big | Get file → |
For 8GB VRAM, use Q8_0 (0.85 GB file, 1.4 GB memory at 8k context). For 16GB VRAM, BF16 (1.59 GB file, 2.1 GB memory) offers a good balance. For 80GB VRAM, MXFP4 (63.39 GB file, 63.9 GB memory) allows the model to run on a single 80GB GPU.
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 BF16 (1.6 GB file, about 2.1 GB in use).
- 6 GB VRAM: the best quant that fits is BF16 (1.6 GB file, about 2.1 GB in use).
- 8 GB VRAM: the best quant that fits is BF16 (1.6 GB file, about 2.1 GB in use).
- 12 GB VRAM: the best quant that fits is BF16 (1.6 GB file, about 2.1 GB in use).
- 16 GB VRAM: the best quant that fits is BF16 (1.6 GB file, about 2.1 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (1.6 GB file, about 2.1 GB in use).
- 32 GB VRAM: the best quant that fits is BF16 (1.6 GB file, about 2.1 GB in use).
- 48 GB VRAM: the best quant that fits is BF16 (1.6 GB file, about 2.1 GB in use).
Which gpt-oss-120b quant should you choose?
BF16 (1.6 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
If memory is tight, the smallest file is Q8_0 at 0.8 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
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 2.1 GB at BF16 with an 8K context window. That is the 1.6 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 BF16: the 1.6 GB file needs about 2.1 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: Q8_0 is 0.8 GB, BF16 is 1.6 GB, MXFP4 is 63.4 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 0.0 GB at 8K and 0.1 GB at 32K.
Where can I download gpt-oss-120b GGUF?
The files are on Hugging Face in the hrm-labs/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 Q8_0 on 8 GB VRAM?
Yes, Q8_0 requires 1.4 GB memory at 8k context, which fits within 8 GB VRAM.
Does this model support vision?
No, gpt‑oss‑120b does not have vision capabilities.
What is the difference between Q8_0 and BF16?
Q8_0 is a full‑precision quantization with a 0.85 GB file, while BF16 uses 16‑bit floating point with a 1.59 GB file and slightly higher memory usage.