GP

gpt oss coder 20B

gpt-ossGGUF by benhaotangUpdated 2025-08-22
Download on Hugging Face
Parameters20.9B
Context128K
Layers24
Architecturegpt-oss
Smallest quant12.1 GB
Quick answer

gpt oss coder 20B needs about 13.0 GB of memory at MXFP4_MOE (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 (MXFP4_MOE) to 13.8 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.

gpt oss coder 20B is a 20.9B-parameter gpt-oss model in GGUF format, quantized by benhaotang. Its trained context length is 128K tokens. The repository has 2 quant files, from 12.1 GB (MXFP4_MOE) to 13.8 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
MXFP4_MOE12.1 GB 13.0 GB
Too big Get file →
F1613.8 GB 14.7 GB
Too big Get file →

What GPU do you need for gpt oss coder 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 F16 (13.8 GB file, about 14.7 GB in use).

Which gpt oss coder 20B quant should you choose?

MXFP4_MOE (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

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

Source

Quantized bybenhaotang
Familygpt-oss
Licenseapache-2.0
Downloads (HF)38
Last updated2025-08-22

Frequently asked questions about gpt oss coder 20B

How much VRAM does gpt oss coder 20B need?

About 13.0 GB at MXFP4_MOE 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 coder 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 gpt oss coder 20B GGUF?

It depends on the quant: MXFP4_MOE is 12.1 GB, F16 is 13.8 GB.

What context length does gpt oss coder 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 coder 20B GGUF?

The files are on Hugging Face in the benhaotang/gpt-oss-coder-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 gpt oss coder 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-coder-20b

Similar models

Browse all →

More from benhaotang

All by benhaotang →

More gpt-oss models

All gpt-oss →

Other medium models

All medium models →