Openai_Gpt Oss 20b needs about 13.0 GB of memory at MXFP4 (a 12.1 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.
OpenAI GPT‑OSS 20B, 20 billion‑parameter MoE model
GPT‑OSS 20B is a 20 billion‑parameter mixture‑of‑experts model trained on the harmony response format. It is available under an Apache 2.0 license and can be fine‑tuned or used for agentic tasks such as function calling and code execution.
Good at
- Reasoning with chain‑of‑thought
- Agentic function calling
- Fine‑tuning for custom tasks
Limits
- Requires 16 GB VRAM with MXFP4 quant
- No vision support
- Only works with harmony format
Best for
- Local inference on 16 GB GPUs
- Fine‑tuning for specialized applications
- Agentic workflows with function calling
Who it’s for. Developers and researchers who need a large, open‑weight model for reasoning or agentic tasks and can run it on a single 16 GB GPU. The model is suitable for experimentation, customization, and commercial deployment under Apache 2.0.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| MXFP4 | 12.1 GB | 13.0 GB | Too big | Get file → |
The provided MXFP4 quantization file is 12.11 GB and requires about 13 GB of VRAM at 8 k context. For 8 GB VRAM, a smaller quantization would be needed, which is not available. For 16 GB VRAM, MXFP4 is suitable.
What GPU do you need for Openai_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 MXFP4 (12.1 GB file, about 13.0 GB in use).
Which Openai_Gpt Oss 20b quant should you choose?
MXFP4 (12.1 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 20b
How much VRAM does Openai_Gpt Oss 20b need?
About 13.0 GB at MXFP4 with an 8K context window. That is the 12.1 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 20b on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 13.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Openai_Gpt Oss 20b GGUF?
It depends on the quant: MXFP4 is 12.1 GB.
What context length does Openai_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 Openai_Gpt Oss 20b GGUF?
The files are on Hugging Face in the lmstudio-community/gpt-oss-20b-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 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 this model on 8 GB VRAM?
No, the MXFP4 quantized model requires about 13 GB VRAM at 8 k context, which exceeds 8 GB.
What license does this model use?
Apache 2.0, allowing free use, modification, and commercial deployment.
Does the model support vision inputs?
No, the model only supports text inputs and requires the harmony response format.