Uigen GGUF models
97 GGUF models in the Uigen family, quantized by 26 uploaders. Sizes run from 161M to 32.8B parameters. The longest trained context is 256K tokens.
About the Uigen GGUF models
Uigen is represented on ggufmodels.com by 97 GGUF models, quantized by 26 uploaders on Hugging Face. The most downloaded are UIGEN T3 32B Preview, UIGEN T3.1 8B Full Demo No Reasoning and UIGEN X 8B. Parameter counts run from 161M to 32.8B, and the longest trained context window is 256K tokens.
A Q4_K_M file of a Uigen model is between 1.9 to 19.9 GB, which is the quant most people start with. Most files come from mradermacher (45), DevQuasar (10) and smirki (8). The quants you will meet most often are Q4_K_M (80), Q6_K (72), Q5_K_M (72) and Q2_K (72), where the number is how many models offer that quant.
Frequently asked questions
Which Uigen GGUF should I download?
The most downloaded Uigen GGUF here is UIGEN T3 32B Preview. 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 Uigen model need?
Q4_K_M files of Uigen models on this site range from 1.9 to 19.9 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 Uigen GGUF files come from?
The most common quantizers here are mradermacher, DevQuasar and smirki. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.