GP

Michaelwaves Amoral GPT OSS 112E

gpt-ossGGUF by mradermacherUpdated 2026-01-21
Download on Hugging Face
Parameters102B
Context128K
Layers36
Architecturegpt-oss
Smallest quant55.7 GB
Quick answer

Michaelwaves Amoral GPT OSS 112E needs about 78.2 GB of memory at Q4_K_M (a 77.1 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 12 quants, from 55.7 GB (MXFP4_MOE) to 109.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 2.4 GB.

Michaelwaves Amoral GPT OSS 112E is a 102B-parameter gpt-oss model in GGUF format, quantized by mradermacher. Its trained context length is 128K tokens. The repository has 12 quant files, from 55.7 GB (MXFP4_MOE) to 109.0 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
MXFP4_MOE55.7 GB 56.9 GB
Too big Get file →
Q3_K_S58.1 GB 59.2 GB
Too big Get file →
Q2_K58.1 GB 59.2 GB
Too big Get file →
IQ4_XS58.8 GB 59.9 GB
Too big Get file →
Q3_K_M62.4 GB 63.5 GB
Too big Get file →
Q3_K_L64.4 GB 65.6 GB
Too big Get file →
Q4_K_S71.0 GB 72.1 GB
Too big Get file →
Q4_K_M77.1 GB 78.2 GB
Too big Get file →
Q5_K_S77.2 GB 78.3 GB
Too big Get file →
Q5_K_M82.4 GB 83.5 GB
Too big Get file →
Q6_K108.9 GB 110.0 GB
Too big Get file →
Q8_0109.0 GB 110.2 GB
Too big Get file →

What GPU do you need for Michaelwaves Amoral GPT OSS 112E?

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: no quant fits at an 8K context.
  • 48 GB VRAM: no quant fits at an 8K context.

Which Michaelwaves Amoral GPT OSS 112E quant should you choose?

Q4_K_M is the usual starting point for Michaelwaves Amoral GPT OSS 112E: it balances file size and quality well. Here it is a 77.1 GB file.

The Q8_0 file is 109.0 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 55.7 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
Parameters102B (approximate, mixture of experts)
Layers36
Trained context131,072 tokens
KV cache (fp16)72 KB per token

Source

Quantized bymradermacher
Familygpt-oss
Licenseapache-2.0
Downloads (HF)75
Last updated2026-01-21

Frequently asked questions about Michaelwaves Amoral GPT OSS 112E

How much VRAM does Michaelwaves Amoral GPT OSS 112E need?

About 78.2 GB at Q4_K_M with an 8K context window. That is the 77.1 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 Michaelwaves Amoral GPT OSS 112E on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 56.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Michaelwaves Amoral GPT OSS 112E GGUF?

It depends on the quant: MXFP4_MOE is 55.7 GB, Q3_K_S is 58.1 GB, Q2_K is 58.1 GB, IQ4_XS is 58.8 GB, Q3_K_M is 62.4 GB, Q3_K_L is 64.4 GB and 6 more.

What context length does Michaelwaves Amoral GPT OSS 112E support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.6 GB at 8K and 2.4 GB at 32K.

Where can I download Michaelwaves Amoral GPT OSS 112E GGUF?

The files are on Hugging Face in the mradermacher/michaelwaves-Amoral-GPT-OSS-112E-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 Michaelwaves Amoral GPT OSS 112E 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 michaelwaves-Amoral-GPT-OSS-112E

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More gpt-oss models

All gpt-oss →

Other large models

All large models →