GP

gpt-oss-20b-VISION-v2

gpt-ossGGUF by SoAIHQUpdated 2026-10-24
Download on Hugging Face
Parameters20.9B
Context128K
Layers24
Architecturegpt-oss
Smallest quant13.8 GB
Quick answer

gpt-oss-20b-VISION-v2 needs about 14.7 GB of memory at MXFP4 (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.

OpenAI gpt-oss 20b VISION v2 model in GGUF format

gpt-oss-20b-VISION-v2 is a 20.9B parameter model with vision, reasoning, and tool use abilities. It is released under Apache 2.0 and is compatible with llama.cpp and SoAI. The model uses MXFP4 quantization and supports a 131072 token context.

Good at

  • Vision and image understanding
  • Reasoning and chain‑of‑thought
  • Tool calling and structured outputs

Limits

  • No vision support in other quantizations
  • Requires 16GB+ VRAM for MXFP4
  • No other quantizations available

Best for

  • Local inference with GPU memory <16GB
  • Vision‑enabled agentic tasks
  • Fine‑tuning for specialized use cases

Who it’s for. Developers and researchers needing an open‑weight GPT‑style model with vision and tool‑calling capabilities. The Apache 2.0 license allows commercial deployment and customization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
MXFP413.8 GB 14.7 GB
Too big Get file →

The only available quant is MXFP4, file size 13.79 GB, estimated memory 14.7 GB at 8K context. It fits on GPUs with 16 GB VRAM or more. For lower memory budgets, no alternative quant is provided.

What GPU do you need for gpt-oss-20b-VISION-v2?

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-VISION-v2 quant should you choose?

MXFP4 (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 bySoAIHQ
Familygpt-oss
Licenseapache-2.0
Downloads (HF)1,810
Last updated2026-10-24

Frequently asked questions about gpt-oss-20b-VISION-v2

How much VRAM does gpt-oss-20b-VISION-v2 need?

About 14.7 GB at MXFP4 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 gpt-oss-20b-VISION-v2 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 gpt-oss-20b-VISION-v2 GGUF?

It depends on the quant: MXFP4 is 13.8 GB.

What context length does gpt-oss-20b-VISION-v2 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-VISION-v2 GGUF?

The files are on Hugging Face in the SoAIHQ/gpt-oss-20b-VISION-v2-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-VISION-v2 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?

No. The MXFP4 quant requires approximately 14.7 GB of VRAM at 8K context, so 8 GB is insufficient.

Does it support vision?

Yes. The model includes image input capabilities and requires the mmproj-gpt-oss-20b-VIS component.

What license applies?

Apache 2.0, allowing free use, modification, and commercial deployment.

Other GGUFs of gpt-oss-20b

Similar models

Browse all →

More from SoAIHQ

All by SoAIHQ →

More gpt-oss models

All gpt-oss →

Other medium models

All medium models →