GP

Gpt Oss 20b

gpt-ossGGUF by bartowskiUpdated 2025-08-05
Download on Hugging Face
Parameters20.9B
Context128K
Layers24
Architecturegpt-oss
Smallest quant12.1 GB
Quick answer

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.

GPT‑OSS 20B – 20 billion‑parameter open‑weight model with MXFP4 quantization

GPT‑OSS 20B is a 20 billion‑parameter open‑weight model from OpenAI, designed for reasoning, agentic tasks, and developer use. It is post‑trained with MXFP4 quantization, enabling inference within 16 GB of memory on a single GPU. The model follows the harmony response format and supports chain‑of‑thought reasoning.

Good at

  • Reasoning and chain‑of‑thought
  • Agentic tasks like function calling and code execution
  • Fine‑tuning for custom applications

Limits

  • Requires harmony response format
  • No vision support
  • Large memory requirement for full context

Best for

  • Low‑latency local inference
  • Fine‑tuning for specialized domains
  • Agentic applications with function calling

Who it’s for. Developers and researchers needing an open‑weight GPT‑style model for reasoning and agentic tasks. The Apache 2.0 license allows commercial use and customization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
MXFP412.1 GB 13.0 GB
Too big Get file →

The MXFP4 quantized file is 12.11 GB and needs about 13 GB of VRAM at 8 k context. For 8 GB VRAM, the model cannot run. For 16 GB VRAM, MXFP4 is suitable. No other quants are available.

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 MXFP4 (12.1 GB file, about 13.0 GB in use).

Which 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

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

Source

Quantized bybartowski
Familygpt-oss
Licenseapache-2.0
Downloads (HF)15,679
Last updated2025-08-05

Frequently asked questions about Gpt Oss 20b

How much VRAM does 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 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 Gpt Oss 20b GGUF?

It depends on the quant: MXFP4 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 bartowski/openai_gpt-oss-20b-GGUF-MXFP4-Experimental 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?

No. The MXFP4 quantized model requires approximately 13 GB of VRAM at 8 k context.

What format must I use for prompts?

Prompts must follow the harmony response format; other formats may not work correctly.

Is the model fine‑tunable?

Yes, the model can be fine‑tuned for specific use cases.

Other GGUFs of gpt-oss-20b

Similar models

Browse all →

More from bartowski

All by bartowski →

More gpt-oss models

All gpt-oss →

Other medium models

All medium models →