Multilingual GGUF models
98 GGUF models in the Multilingual family, quantized by 61 uploaders. Sizes run from 23M to 8.03B parameters. The longest trained context is 128K tokens.
About the Multilingual GGUF models
Multilingual is represented on ggufmodels.com by 98 GGUF models, quantized by 61 uploaders on Hugging Face. The most downloaded are multilingual e5 large instruct, multilingual e5 small and multilingual e5 small. Parameter counts run from 23M to 8.03B, and the longest trained context window is 128K tokens.
A Q4_K_M file of a Multilingual model is between 0.0 to 4.9 GB, which is the quant most people start with. Most files come from mradermacher (13), keisuke-miyako (9) and dinab (5). The quants you will meet most often are Q8_0 (49), Q4_K_M (42), F16 (24) and Q6_K (19), where the number is how many models offer that quant.
Frequently asked questions
Which Multilingual GGUF should I download?
The most downloaded Multilingual GGUF here is multilingual e5 large 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 Multilingual model need?
Q4_K_M files of Multilingual models on this site range from 0.0 to 4.9 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 Multilingual GGUF files come from?
The most common quantizers here are mradermacher, keisuke-miyako and dinab. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.