OL

OLMo 7B 0724 Hf

OLMoGGUF by aifoundry-orgUpdated 2024-08-14
Download on Hugging Face
Parameters6.89B
Context4K
Layers32
Architectureolmo
Smallest quant1.6 GB
Quick answer

OLMo 7B 0724 Hf needs about 8.2 GB of memory at Q3_K (a 3.4 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 11 quants, from 1.6 GB (IQ1_S) to 13.8 GB (F16).

OLMo 7B 0724 Hf is a 6.89B-parameter OLMo model in GGUF format, quantized by aifoundry-org. Its trained context length is 4K tokens. The repository has 11 quant files, from 1.6 GB (IQ1_S) to 13.8 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.6 GB 4.3 GB
Fits Get file →
IQ1_M1.7 GB 4.4 GB
Fits Get file →
IQ2_S2.3 GB 4.9 GB
Fits Get file →
IQ2_M2.4 GB 5.1 GB
Fits Get file →
Q2_K2.6 GB 5.3 GB
Fits Get file →
Q3_K3.4 GB 6.0 GB
Fits Get file →
Q4_K4.2 GB 6.8 GB
Fits Get file →
Q5_K4.9 GB 7.5 GB
Tight Get file →
Q6_K5.7 GB 8.3 GB
Too big Get file →
Q8_07.3 GB 10.0 GB
Too big Get file →
F1613.8 GB 16.4 GB
Too big Get file →

What GPU do you need for OLMo 7B 0724 Hf?

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: the best quant that fits is Q2_K (2.6 GB file, about 7.4 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (5.7 GB file, about 10.4 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (7.3 GB file, about 12.1 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (13.8 GB file, about 18.6 GB in use).

Which OLMo 7B 0724 Hf quant should you choose?

Q3_K (3.4 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

If memory is tight, the smallest file is IQ1_S at 1.6 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureolmo
Parameters6.89B
Layers32
Trained context4,096 tokens
KV cache (fp16)512 KB per token

Source

Quantized byaifoundry-org
FamilyOLMo
Licenseapache-2.0
Downloads (HF)299
Last updated2024-08-14

Frequently asked questions about OLMo 7B 0724 Hf

How much VRAM does OLMo 7B 0724 Hf need?

About 8.2 GB at Q3_K with an 8K context window. That is the 3.4 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 7B 0724 Hf on an 8 GB GPU?

Yes, with Q2_K: the 2.6 GB file needs about 7.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of OLMo 7B 0724 Hf GGUF?

It depends on the quant: IQ1_S is 1.6 GB, IQ1_M is 1.7 GB, IQ2_S is 2.3 GB, IQ2_M is 2.4 GB, Q2_K is 2.6 GB, Q3_K is 3.4 GB and 5 more.

What context length does OLMo 7B 0724 Hf support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.3 GB at 8K and 2.1 GB at 4K.

Where can I download OLMo 7B 0724 Hf GGUF?

The files are on Hugging Face in the aifoundry-org/OLMo-7B-0724-hf-Quantized 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 7B 0724 Hf 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-7B-0724-hf

Similar models

Browse all →

More from aifoundry-org

All by aifoundry-org →

More OLMo models

All OLMo →

Other small models

All small models →