GP

Gpt Oss 46b

gpt-ossGGUF by mradermacherUpdated 2025-12-18
Download on Hugging Face
Parameters45.7B
Context128K
Layers24
Architecturegpt-oss
Smallest quant25.8 GB
Quick answer

Gpt Oss 46b needs about 35.4 GB of memory at Q4_K_M (a 34.5 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 12 quants, from 25.8 GB (MXFP4_MOE) to 48.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.

Gpt Oss 46b is a 45.7B-parameter gpt-oss model in GGUF format, quantized by mradermacher. Its trained context length is 128K tokens. The repository has 12 quant files, from 25.8 GB (MXFP4_MOE) to 48.6 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
MXFP4_MOE25.8 GB 26.7 GB
Too big Get file →
Q3_K_S26.1 GB 27.0 GB
Too big Get file →
Q2_K26.2 GB 27.1 GB
Too big Get file →
IQ4_XS26.5 GB 27.4 GB
Too big Get file →
Q3_K_M28.0 GB 28.9 GB
Too big Get file →
Q3_K_L29.0 GB 29.9 GB
Too big Get file →
Q4_K_S31.9 GB 32.8 GB
Too big Get file →
Q4_K_M34.5 GB 35.4 GB
Too big Get file →
Q5_K_S34.6 GB 35.5 GB
Too big Get file →
Q5_K_M36.8 GB 37.7 GB
Too big Get file →
Q6_K48.5 GB 49.4 GB
Too big Get file →
Q8_048.6 GB 49.5 GB
Too big Get file →

What GPU do you need for Gpt Oss 46b?

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: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is Q3_K_L (29.0 GB file, about 29.9 GB in use).
  • 48 GB VRAM: the best quant that fits is Q5_K_M (36.8 GB file, about 37.7 GB in use).

Which Gpt Oss 46b quant should you choose?

Q4_K_M is the usual starting point for Gpt Oss 46b: it balances file size and quality well. Here it is a 34.5 GB file.

The Q8_0 file is 48.6 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 MXFP4_MOE at 25.8 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
Parameters45.7B (approximate, mixture of experts)
Layers24
Trained context131,072 tokens
KV cache (fp16)48 KB per token

Source

Quantized bymradermacher
Familygpt-oss
Licenseapache-2.0
Downloads (HF)304
Last updated2025-12-18

Frequently asked questions about Gpt Oss 46b

How much VRAM does Gpt Oss 46b need?

About 35.4 GB at Q4_K_M with an 8K context window. That is the 34.5 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 46b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 26.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Gpt Oss 46b GGUF?

It depends on the quant: MXFP4_MOE is 25.8 GB, Q3_K_S is 26.1 GB, Q2_K is 26.2 GB, IQ4_XS is 26.5 GB, Q3_K_M is 28.0 GB, Q3_K_L is 29.0 GB and 6 more.

What context length does Gpt Oss 46b 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 46b GGUF?

The files are on Hugging Face in the mradermacher/gpt-oss-46b-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 46b 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-46b

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More gpt-oss models

All gpt-oss →

Other large models

All large models →