OL

OLMo 2 1124 13B Instruct

OLMoGGUF by CCATresearchUpdated 2024-11-27
Download on Hugging Face
Parameters13.7B
Context4K
Layers40
Architectureolmo2
Smallest quant7.9 GB
Quick answer

OLMo 2 1124 13B Instruct needs about 21.8 GB of memory at Q8_0 (a 14.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 3 quants, from 7.9 GB (Q4_0) to 27.4 GB (F16).

OLMo 2 1124 13B Instruct is a 13.7B-parameter OLMo model in GGUF format, quantized by CCATresearch. Its trained context length is 4K tokens. The repository has 3 quant files, from 7.9 GB (Q4_0) to 27.4 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_07.9 GB 11.7 GB
Too big Get file →
Q8_014.6 GB 18.4 GB
Too big Get file →
F1627.4 GB 31.3 GB
Too big Get file →

What GPU do you need for OLMo 2 1124 13B Instruct?

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_0 (7.9 GB file, about 15.1 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (14.6 GB file, about 21.8 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (14.6 GB file, about 21.8 GB in use).
  • 48 GB VRAM: the best quant that fits is F16 (27.4 GB file, about 34.6 GB in use).

Which OLMo 2 1124 13B Instruct quant should you choose?

Q8_0 (14.6 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

If memory is tight, the smallest file is Q4_0 at 7.9 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

Architectureolmo2
Parameters13.7B
Layers40
Trained context4,096 tokens
KV cache (fp16)800 KB per token

Source

Quantized byCCATresearch
FamilyOLMo
Licenseapache-2.0
Downloads (HF)45
Last updated2024-11-27

Frequently asked questions about OLMo 2 1124 13B Instruct

How much VRAM does OLMo 2 1124 13B Instruct need?

About 21.8 GB at Q8_0 with an 8K context window. That is the 14.6 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 OLMo 2 1124 13B Instruct on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of OLMo 2 1124 13B Instruct GGUF?

It depends on the quant: Q4_0 is 7.9 GB, Q8_0 is 14.6 GB, F16 is 27.4 GB.

What context length does OLMo 2 1124 13B Instruct support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 6.7 GB at 8K and 3.4 GB at 4K.

Where can I download OLMo 2 1124 13B Instruct GGUF?

The files are on Hugging Face in the CCATresearch/OLMo-2-1124-13B-Instruct repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does OLMo 2 1124 13B Instruct 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 OLMo-2-1124-13B-Instruct

Similar models

Browse all →

More from CCATresearch

All by CCATresearch →

More OLMo models

All OLMo →

Other medium models

All medium models →