Gpt Oss 20b Sft Mxfp4 needs about 13.0 GB of memory at IQ4_XS (a 12.1 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 2 quants, from 12.1 GB (IQ4_XS) to 13.8 GB (MXFP4). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.
Gpt Oss 20b Sft Mxfp4 is a 20.9B-parameter gpt-oss model in GGUF format, quantized by ospost. Its trained context length is 128K tokens. The repository has 2 quant files, from 12.1 GB (IQ4_XS) to 13.8 GB (MXFP4).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ4_XS | 12.1 GB | 13.0 GB | Too big | Get file → | |
| MXFP4 | 13.8 GB | 14.7 GB | Too big | Get file → |
What GPU do you need for Gpt Oss 20b Sft Mxfp4?
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 (13.8 GB file, about 14.7 GB in use).
Which Gpt Oss 20b Sft Mxfp4 quant should you choose?
IQ4_XS (12.1 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Gpt Oss 20b Sft Mxfp4
How much VRAM does Gpt Oss 20b Sft Mxfp4 need?
About 13.0 GB at IQ4_XS 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 Gpt Oss 20b Sft Mxfp4 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 Gpt Oss 20b Sft Mxfp4 GGUF?
It depends on the quant: IQ4_XS is 12.1 GB, MXFP4 is 13.8 GB.
What context length does Gpt Oss 20b Sft Mxfp4 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 Sft Mxfp4 GGUF?
The files are on Hugging Face in the ospost/gpt-oss-20b-sft-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.