Gpt Oss 20b needs about 12.7 GB of memory at MXFP4 (a 11.8 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 5 quants, from 11.5 GB (MXFP4) to 12.1 GB (IQ4_NL). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.
OpenAI gpt-oss 20b model for coding, reasoning, and tool use
The gpt-oss 20b model contains 20.9B parameters and is a mixture of experts. It was trained on 131072 context tokens and supports coding, reasoning, and tool calls. The model is released under the Apache-2.0 license and requires the harmony format for correct operation.
Good at
- Coding tasks
- Reasoning with chain-of-thought
- Tool and function calling
Limits
- Requires harmony format
- Large VRAM for full precision
- No vision support
Best for
- Local code generation
- Agentic workflows
- Fine‑tuning for specialized tasks
Who it’s for. Developers and researchers who need a versatile, open‑weight model for local deployment. The model is suitable for those who want to experiment with function calling, web browsing, and Python execution in a controlled environment.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| MXFP4 | 11.5 GB | 12.4 GB | Too big | Get file → | |
| IQ4_NL | 11.8 GB | 12.7 GB | Too big | Get file → | |
| MXFP4 | 11.8 GB | 12.7 GB | Too big | Get file → | |
| MXFP4 | 11.9 GB | 12.8 GB | Too big | Get file → | |
| IQ4_NL | 12.1 GB | 13.0 GB | Too big | Get file → |
For 8 GB VRAM, use the IQ4_NL quant with file size 11.82 GB, estimating 12.7 GB memory at 8 k context. For 12 GB VRAM, the MXFP4 quant of 11.93 GB file size uses about 12.8 GB memory. Memory estimates are approximate.
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 IQ4_NL (12.1 GB file, about 13.0 GB in use).
Which Gpt Oss 20b quant should you choose?
MXFP4 (11.8 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.
If memory is tight, the smallest file is MXFP4 at 11.5 GB, with the quality trade-offs that come with fewer bits. 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 20b
How much VRAM does Gpt Oss 20b need?
About 12.7 GB at MXFP4 with an 8K context window. That is the 11.8 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: MXFP4 is 11.5 GB, IQ4_NL is 11.8 GB, MXFP4 is 11.8 GB, MXFP4 is 11.9 GB, IQ4_NL is 12.1 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 diablomike20/Openai_gpt-oss-20b-CODEX-CODER 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?
Yes, using the IQ4_NL quant (11.82 GB) will use about 12.7 GB memory at 8 k context, which is close to 8 GB but may require swapping.
Does the model support vision?
No, the model does not include vision capabilities.
What license does the model use?
The model is released under the Apache-2.0 license.