Hunyuan GGUF models
85 GGUF models in the Hunyuan family, quantized by 40 uploaders. Sizes run from 539M to 80.4B parameters. The longest trained context is 256K tokens.
About the Hunyuan GGUF models
Hunyuan is represented on ggufmodels.com by 85 GGUF models, quantized by 40 uploaders on Hugging Face. The most downloaded are Hunyuan MT 7B, Hunyuan-MT-7B and Hunyuan MT 7B. Parameter counts run from 539M to 80.4B, and the longest trained context window is 256K tokens.
A Q4_K_M file of a Hunyuan model is between 0.4 to 49.3 GB, which is the quant most people start with. Most files come from mradermacher (19), DevQuasar (7) and gabriellarson (5). The quants you will meet most often are Q4_K_M (62), Q8_0 (56), Q3_K_M (48) and Q2_K (46), where the number is how many models offer that quant.
Frequently asked questions
Which Hunyuan GGUF should I download?
The most downloaded Hunyuan GGUF here is Hunyuan MT 7B. 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 Hunyuan model need?
Q4_K_M files of Hunyuan models on this site range from 0.4 to 49.3 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 Hunyuan GGUF files come from?
The most common quantizers here are mradermacher, DevQuasar and gabriellarson. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.