Yi GGUF models
630 GGUF models in the Yi family, quantized by 104 uploaders. Sizes run from 1.48B to 71.2B parameters. The longest trained context is 256K tokens.
About the Yi GGUF models
Yi is represented on ggufmodels.com by 630 GGUF models, quantized by 104 uploaders on Hugging Face. The most downloaded are models--01-ai--Yi-1.5-6B-Chat, brucethemoose_yi-34b-200k-dare-megamerge-v8 and Yi 6B Chat. Parameter counts run from 1.48B to 71.2B, and the longest trained context window is 256K tokens.
A Q4_K_M file of a Yi model is between 1.0 to 42.6 GB, which is the quant most people start with. Most files come from mradermacher (200), RichardErkhov (76) and tensorblock (49). The quants you will meet most often are Q4_K_M (483), Q2_K (455), Q5_K_M (433) and Q6_K (431), where the number is how many models offer that quant.
Frequently asked questions
Which Yi GGUF should I download?
The most downloaded Yi GGUF here is models--01-ai--Yi-1.5-6B-Chat. 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 Yi model need?
Q4_K_M files of Yi models on this site range from 1.0 to 42.6 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 Yi GGUF files come from?
The most common quantizers here are mradermacher, RichardErkhov and tensorblock. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.