GP

GPT OSS 26E Abliterated

gpt-ossGGUF by mradermacherUpdated 2026-02-18
Download on Hugging Face
Parameters17.3B
Context128K
Layers24
Architecturegpt-oss
Smallest quant10.0 GB
Quick answer

GPT OSS 26E Abliterated needs about 14.0 GB of memory at Q4_K_M (a 13.1 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 12 quants, from 10.0 GB (Q3_K_S) to 18.4 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.

GPT OSS 26E Abliterated is a 17.3B-parameter gpt-oss model in GGUF format, quantized by mradermacher. Its trained context length is 128K tokens. The repository has 12 quant files, from 10.0 GB (Q3_K_S) to 18.4 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_S10.0 GB 10.9 GB
Too big Get file →
Q2_K10.0 GB 10.9 GB
Too big Get file →
IQ4_XS10.2 GB 11.1 GB
Too big Get file →
MXFP4_MOE10.2 GB 11.1 GB
Too big Get file →
Q3_K_M10.7 GB 11.6 GB
Too big Get file →
Q3_K_L11.1 GB 12.0 GB
Too big Get file →
Q4_K_S12.2 GB 13.1 GB
Too big Get file →
Q4_K_M13.1 GB 14.0 GB
Too big Get file →
Q5_K_S13.2 GB 14.1 GB
Too big Get file →
Q5_K_M14.0 GB 14.9 GB
Too big Get file →
Q6_K18.4 GB 19.3 GB
Too big Get file →
Q8_018.4 GB 19.4 GB
Too big Get file →

What GPU do you need for GPT OSS 26E Abliterated?

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: the best quant that fits is Q3_K_L (11.1 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q5_K_M (14.0 GB file, about 14.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (18.4 GB file, about 19.4 GB in use).

Which GPT OSS 26E Abliterated quant should you choose?

Q4_K_M is the usual starting point for GPT OSS 26E Abliterated: it balances file size and quality well. Here it is a 13.1 GB file.

The Q8_0 file is 18.4 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 Q3_K_S at 10.0 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegpt-oss
Parameters17.3B (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)161
Last updated2026-02-18

Frequently asked questions about GPT OSS 26E Abliterated

How much VRAM does GPT OSS 26E Abliterated need?

About 14.0 GB at Q4_K_M with an 8K context window. That is the 13.1 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 26E Abliterated on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of GPT OSS 26E Abliterated GGUF?

It depends on the quant: Q3_K_S is 10.0 GB, Q2_K is 10.0 GB, IQ4_XS is 10.2 GB, MXFP4_MOE is 10.2 GB, Q3_K_M is 10.7 GB, Q3_K_L is 11.1 GB and 6 more.

What context length does GPT OSS 26E Abliterated 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 26E Abliterated GGUF?

The files are on Hugging Face in the mradermacher/GPT-OSS-26E-Abliterated-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 26E Abliterated 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-26E-Abliterated

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More gpt-oss models

All gpt-oss →

Other medium models

All medium models →