OLMo GGUF models
756 GGUF models in the OLMo family, quantized by 151 uploaders. Sizes run from 7M to 32.2B parameters. The longest trained context is 128K tokens.
About the OLMo GGUF models
OLMo is represented on ggufmodels.com by 756 GGUF models, quantized by 151 uploaders on Hugging Face. The most downloaded are allenai_olmOCR 2 7B 1025, olmOCR 2 7B 1025 and OLMo 2 1124 13B Instruct. Parameter counts run from 7M to 32.2B, and the longest trained context window is 128K tokens.
A Q4_K_M file of a OLMo model is between 0.0 to 19.5 GB, which is the quant most people start with. Most files come from mradermacher (367), tensorblock (31) and RichardErkhov (25). The quants you will meet most often are Q4_K_M (597), Q6_K (533), Q2_K (530) and Q5_K_M (509), where the number is how many models offer that quant.
Frequently asked questions
Which OLMo GGUF should I download?
The most downloaded OLMo GGUF here is allenai_olmOCR 2 7B 1025. Pick the size that fits your GPU first, then choose a quant: Q4_K_M is the usual starting point, and Q5_K_M or Q6_K give more quality if you have memory to spare. The VRAM pages below list what fits each GPU.
How much VRAM does a OLMo model need?
Q4_K_M files of OLMo models on this site range from 0.0 to 19.5 GB. Add the KV cache for your context length and about 0.5 GB for the runtime, which usually means 1.5 to 3 GB on top of the file at an 8K context.
Where do OLMo GGUF files come from?
The most common quantizers here are mradermacher, tensorblock and RichardErkhov. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.