Huihui GGUF models
202 GGUF models in the Huihui family, quantized by 45 uploaders. Sizes run from 447M to 72.7B parameters. The longest trained context is 1024K tokens.
About the Huihui GGUF models
Huihui is represented on ggufmodels.com by 202 GGUF models, quantized by 45 uploaders on Hugging Face. The most downloaded are Cyber Tiel Coder 35B A3B GGUF MTP, Cyber Tiel Coder 35B A3B and Huihui4 8B A4B. Parameter counts run from 447M to 72.7B, and the longest trained context window is 1024K tokens.
A Q4_K_M file of a Huihui model is between 0.6 to 47.4 GB, which is the quant most people start with. Most files come from mradermacher (109), noctrex (13) and Manojb (12). The quants you will meet most often are Q4_K_M (152), Q6_K (139), Q5_K_M (135) and Q3_K_M (133), where the number is how many models offer that quant.
Frequently asked questions
Which Huihui GGUF should I download?
The most downloaded Huihui GGUF here is Cyber Tiel Coder 35B A3B GGUF MTP. 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 Huihui model need?
Q4_K_M files of Huihui models on this site range from 0.6 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 Huihui GGUF files come from?
The most common quantizers here are mradermacher, noctrex and Manojb. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.