Eurollm GGUF models
99 GGUF models in the Eurollm family, quantized by 38 uploaders. Sizes run from 18M to 22.6B parameters. The longest trained context is 32K tokens.
About the Eurollm GGUF models
Eurollm is represented on ggufmodels.com by 99 GGUF models, quantized by 38 uploaders on Hugging Face. The most downloaded are EuroLLM 1.7B Instruct, EuroLLM 22B Instruct 2512 and EuroLLM 9B Instruct. Parameter counts run from 18M to 22.6B, and the longest trained context window is 32K tokens.
A Q4_K_M file of a Eurollm model is between 1.0 to 13.7 GB, which is the quant most people start with. Most files come from mradermacher (37), keisuke-miyako (4) and QuantFactory (4). The quants you will meet most often are Q4_K_M (74), Q8_0 (59), Q5_K_M (54) and Q6_K (53), where the number is how many models offer that quant.
Frequently asked questions
Which Eurollm GGUF should I download?
The most downloaded Eurollm GGUF here is EuroLLM 1.7B Instruct. 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 Eurollm model need?
Q4_K_M files of Eurollm models on this site range from 1.0 to 13.7 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 Eurollm GGUF files come from?
The most common quantizers here are mradermacher, keisuke-miyako and QuantFactory. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.