GP

GPT OSS Swallow 20B RL v0.1

gpt-ossGGUF by mmnga-oUpdated 2026-02-21
Download on Hugging Face
Parameters20.9B
Context128K
Layers24
Architecturegpt-oss
Smallest quant12.1 GB
Quick answer

GPT OSS Swallow 20B RL v0.1 needs about 16.7 GB of memory at Q4_K_M (a 15.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 15 quants, from 12.1 GB (IQ4_XS) to 22.3 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.

GPT OSS Swallow 20B RL v0.1 is a 20.9B-parameter gpt-oss model in GGUF format, quantized by mmnga-o. Its trained context length is 128K tokens. The repository has 15 quant files, from 12.1 GB (IQ4_XS) to 22.3 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ4_XS12.1 GB 13.0 GB
Too big Get file →
Q4_012.1 GB 13.0 GB
Too big Get file →
IQ4_NL12.1 GB 13.0 GB
Too big Get file →
MXFP4_MOE12.1 GB 13.0 GB
Too big Get file →
MXFP4_MOE12.1 GB (2 parts) 13.0 GB
Too big Get file →
IQ3_M12.2 GB 13.1 GB
Too big Get file →
Q3_K_M12.9 GB 13.8 GB
Too big Get file →
Q3_K_L13.3 GB 14.2 GB
Too big Get file →
Q5_014.6 GB 15.5 GB
Too big Get file →
Q4_K_S14.7 GB 15.6 GB
Too big Get file →
Q4_K_M15.8 GB 16.7 GB
Too big Get file →
Q5_K_S15.9 GB 16.8 GB
Too big Get file →
Q5_K_M16.9 GB 17.8 GB
Too big Get file →
Q6_K22.2 GB 23.1 GB
Too big Get file →
Q8_022.3 GB 23.2 GB
Too big Get file →

What GPU do you need for GPT OSS Swallow 20B RL v0.1?

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 Q4_K_S (14.7 GB file, about 15.6 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (22.3 GB file, about 23.2 GB in use).

Which GPT OSS Swallow 20B RL v0.1 quant should you choose?

Q4_K_M is the usual starting point for GPT OSS Swallow 20B RL v0.1: it balances file size and quality well. Here it is a 15.8 GB file.

The Q8_0 file is 22.3 GB, about 1.4 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is IQ4_XS at 12.1 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

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 bymmnga-o
Familygpt-oss
Licenseapache-2.0
Downloads (HF)543
Last updated2026-02-21

Frequently asked questions about GPT OSS Swallow 20B RL v0.1

How much VRAM does GPT OSS Swallow 20B RL v0.1 need?

About 16.7 GB at Q4_K_M with an 8K context window. That is the 15.8 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 Swallow 20B RL v0.1 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 Swallow 20B RL v0.1 GGUF?

It depends on the quant: IQ4_XS is 12.1 GB, Q4_0 is 12.1 GB, IQ4_NL is 12.1 GB, MXFP4_MOE is 12.1 GB, MXFP4_MOE is 12.1 GB, IQ3_M is 12.2 GB and 9 more.

What context length does GPT OSS Swallow 20B RL v0.1 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 Swallow 20B RL v0.1 GGUF?

The files are on Hugging Face in the mmnga-o/GPT-OSS-Swallow-20B-RL-v0.1-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 Swallow 20B RL v0.1 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-Swallow-20B-RL-v0.1

Similar models

Browse all →

More from mmnga-o

All by mmnga-o →

More gpt-oss models

All gpt-oss →

Other medium models

All medium models →