Aya GGUF models
240 GGUF models in the Aya family, quantized by 65 uploaders. Sizes run from 24M to 35B parameters. The longest trained context is 4194304K tokens.
About the Aya GGUF models
Aya is represented on ggufmodels.com by 240 GGUF models, quantized by 65 uploaders on Hugging Face. The most downloaded are Aya Expanse 8b, Aya Expanse 8b and aya-23-8B. Parameter counts run from 24M to 35B, and the longest trained context window is 4194304K tokens.
A Q4_K_M file of a Aya model is between 1.7 to 21.5 GB, which is the quant most people start with. Most files come from mradermacher (67), matrixportalx (28) and am0n666x (12). The quants you will meet most often are Q4_K_M (165), Q2_K (119), Q6_K (115) and Q5_K_M (111), where the number is how many models offer that quant.
Frequently asked questions
Which Aya GGUF should I download?
The most downloaded Aya GGUF here is Aya Expanse 8b. 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 Aya model need?
Q4_K_M files of Aya models on this site range from 1.7 to 21.5 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 Aya GGUF files come from?
The most common quantizers here are mradermacher, matrixportalx and am0n666x. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.