GP

OSS 20B

gpt-ossGGUF by Noah-H309Updated 2026-10-26
Download on Hugging Face
Parameters20.9B
Context128K
Layers24
Architecturegpt-oss
Smallest quant13.8 GB
Quick answer

OSS 20B needs about 14.7 GB of memory at MXFP4_MOE (a 13.8 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.

OSS 20B is a 20.9B-parameter gpt-oss model in GGUF format, quantized by Noah-H309. Its trained context length is 128K tokens. The repository has 1 quant file, from 13.8 GB (MXFP4_MOE) to 13.8 GB (MXFP4_MOE).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
MXFP4_MOE13.8 GB 14.7 GB
Too big Get file →

What GPU do you need for 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_MOE (13.8 GB file, about 14.7 GB in use).

Which OSS 20B quant should you choose?

MXFP4_MOE (13.8 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

Architecturegpt-oss
Parameters20.9B (approximate, mixture of experts)
Layers24
Trained context131,072 tokens
KV cache (fp16)48 KB per token

Source

Quantized byNoah-H309
Familygpt-oss
Licenseapache-2.0
Downloads (HF)269
Last updated2026-10-26

Frequently asked questions about OSS 20B

How much VRAM does OSS 20B need?

About 14.7 GB at MXFP4_MOE with an 8K context window. That is the 13.8 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 OSS 20B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 14.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of OSS 20B GGUF?

It depends on the quant: MXFP4_MOE is 13.8 GB.

What context length does 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 OSS 20B GGUF?

The files are on Hugging Face in the Noah-H309/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 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.

Other GGUFs of gpt-oss-20b

Similar models

Browse all →

More from Noah-H309

All by Noah-H309 →

More gpt-oss models

All gpt-oss →

Other medium models

All medium models →