Gpt-Oss-20B needs about 12.4 GB of memory at Q2_K (a 11.5 GB file) with an 8K context window, so it fits on a 16 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.
20.9B‑parameter GPT‑OSS model with tool‑calling support
Gpt‑Oss‑20B is a 20.9B‑parameter GPT‑OSS model trained on the harmony response format. It supports function calling, web browsing, Python execution, and structured outputs. The model is released under Apache‑2.0.
Good at
- Tool‑based function calling
- Agentic tasks like web browsing
- Structured output generation
Limits
- No vision support
- Requires harmony format
- Large memory footprint
Best for
- Local inference on high‑memory GPUs
- Fine‑tuning for specialized tasks
- Agentic applications needing function calls
Who it’s for. Developers and researchers who need a large, open‑weight GPT‑OSS model for local deployment or fine‑tuning. The Apache‑2.0 license allows commercial use without copyleft restrictions.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 11.5 GB | 12.4 GB | Too big | Get file → |
The available Q2_K quant is 11.47 GB and needs about 12.4 GB of VRAM at 8 k context. For 16 GB VRAM you can run it, but 8 GB VRAM is insufficient. No other quantizations are provided.
What GPU do you need for Gpt-Oss-20B?
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: the best quant that fits is Q2_K (11.5 GB file, about 12.4 GB in use).
Which Gpt-Oss-20B quant should you choose?
Q2_K (11.5 GB) is the middle option in this repository. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Gpt-Oss-20B
How much VRAM does Gpt-Oss-20B need?
About 12.4 GB at Q2_K with an 8K context window. That is the 11.5 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-20B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 12.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Gpt-Oss-20B GGUF?
It depends on the quant: Q2_K is 11.5 GB.
What context length does Gpt-Oss-20B support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.6 GB at 32K.
Where can I download Gpt-Oss-20B GGUF?
The files are on Hugging Face in the oki0ki/gpt-oss-20b 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-20B 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‑20B on 8 GB VRAM?
No, the Q2_K quant requires about 12.4 GB of VRAM at 8 k context.
Does Gpt‑Oss‑20B support function calling?
Yes, it has native tool‑calling capabilities.
Can I use Gpt‑Oss‑20B with llama.cpp?
Yes, the model is supported by llama.cpp and can be run in GGUF format.