GP

Gpt Oss 20b

gpt-ossGGUF by DavidAUUpdated 2025-08-07
Download on Hugging Face
Parameters20.9B
Context128K
Layers24
Architecturegpt-oss
Smallest quant11.5 GB
Quick answer

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 20.9 b parameters and is a mixture of experts. It was trained on 131072 context tokens and is licensed under Apache 2.0. The model supports coding, reasoning, and tool‑based tasks.

Good at

  • Coding tasks
  • Reasoning with chain‑of‑thought
  • Tool calling and structured outputs

Limits

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

Best for

  • Local coding assistants
  • Agentic workflows
  • Fine‑tuning for specialized use cases

Who it’s for. Developers and researchers who need an open‑weight GPT‑style model for local inference or fine‑tuning. The Apache 2.0 license allows commercial use without copyleft restrictions.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
MXFP411.5 GB 12.4 GB
Too big Get file →
IQ4_NL11.8 GB 12.7 GB
Too big Get file →
MXFP411.8 GB 12.7 GB
Too big Get file →
MXFP411.9 GB 12.8 GB
Too big Get file →
IQ4_NL12.1 GB 13.0 GB
Too big Get file →

For 8 GB VRAM, use the IQ4_NL quant (file size 11.82 GB, estimated 12.7 GB memory at 8 k context). For 16 GB VRAM, the MXFP4 quant (file size 11.53 GB, estimated 12.4 GB memory) is suitable. Larger VRAM allows the MXFP4_MOE quants for better performance.

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

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

Source

Quantized byDavidAU
Familygpt-oss
Licenseapache-2.0
Downloads (HF)845
Last updated2025-08-07

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 DavidAU/Openai_gpt-oss-20b-CODER-NEO-CODE-DI-MATRIX-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 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 this model on 8 GB VRAM?

Yes, the IQ4_NL quant uses about 12.7 GB memory at 8 k context, which fits within 8 GB VRAM when using efficient batching.

Does the model support vision tasks?

No, the model does not include vision capabilities.

What license applies to this model?

The model is released under the Apache 2.0 license, allowing free use and modification.

Other GGUFs of gpt-oss-20b

Similar models

Browse all →

More from DavidAU

All by DavidAU →

More gpt-oss models

All gpt-oss →

Other medium models

All medium models →