OL

OlMoE

OLMoGGUF by hhlxm0324Updated 2026-03-07
Download on Hugging Face
Parameters15.7B
Context4K
Layers16
Architectureolmoe
Smallest quant13.8 GB
Quick answer

OlMoE needs about 15.4 GB of memory at its main file (a 13.8 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 3 quants, from 13.8 GB to 31.4 GB.

OlMoE is a 15.7B-parameter OLMo model in GGUF format, quantized by hhlxm0324. Its trained context length is 4K tokens. The repository has 3 quant files, from 13.8 GB to 31.4 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—13.8 GB 14.9 GB
Too big Get file →
—13.8 GB 14.9 GB
Too big Get file →
—31.4 GB 32.5 GB
Too big Get file →

What GPU do you need for OlMoE?

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 the main file (13.8 GB file, about 15.4 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (13.8 GB file, about 15.4 GB in use).
  • 32 GB VRAM: the best quant that fits is the main file (13.8 GB file, about 15.4 GB in use).
  • 48 GB VRAM: the best quant that fits is the main file (31.4 GB file, about 33.0 GB in use).

Which OlMoE quant should you choose?

If memory is tight, the smallest file is the first one in the table at 13.8 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureolmoe
Parameters15.7B (approximate, mixture of experts)
Layers16
Trained context4,096 tokens
KV cache (fp16)128 KB per token

Source

Quantized byhhlxm0324
FamilyOLMo
Repositoryhhlxm0324/OlMoE
Licensemit
Downloads (HF)10
Last updated2026-03-07

Frequently asked questions about OlMoE

How much VRAM does OlMoE need?

About 15.4 GB at its main file 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 OlMoE on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of OlMoE GGUF?

It depends on the quant: file is 13.8 GB, file is 13.8 GB, file is 31.4 GB.

What context length does OlMoE support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.1 GB at 8K and 0.5 GB at 4K.

Where can I download OlMoE GGUF?

The files are on Hugging Face in the hhlxm0324/OlMoE repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does OlMoE use?

Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More OLMo models

All OLMo →

Other medium models

All medium models →