Jais GGUF models
103 GGUF models in the Jais family, quantized by 12 uploaders. Sizes run from 385M to 72.7B parameters. The longest trained context is 512K tokens.
About the Jais GGUF models
Jais is represented on ggufmodels.com by 103 GGUF models, quantized by 12 uploaders on Hugging Face. The most downloaded are Jais-3-32B, Jais-3-32B and Jais-3-MoVA-36B-A4B. Parameter counts run from 385M to 72.7B, and the longest trained context window is 512K tokens.
A Q4_K_M file of a Jais model is between 0.3 to 47.4 GB, which is the quant most people start with. Most files come from mradermacher (63), RichardErkhov (8) and NikolayKozloff (6). The quants you will meet most often are Q4_K_M (90), Q5_K_M (80), Q2_K (77) and Q3_K_M (76), where the number is how many models offer that quant.
Frequently asked questions
Which Jais GGUF should I download?
The most downloaded Jais GGUF here is Jais-3-32B. 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 Jais model need?
Q4_K_M files of Jais models on this site range from 0.3 to 47.4 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 Jais GGUF files come from?
The most common quantizers here are mradermacher, RichardErkhov and NikolayKozloff. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.