Richarderkhov GGUF models
77 GGUF models in the Richarderkhov family, quantized by 1 uploader. Sizes run from 31M to 34.6B parameters. The longest trained context is 128K tokens.
About the Richarderkhov GGUF models
Richarderkhov is represented on ggufmodels.com by 77 GGUF models, quantized by 1 uploader on Hugging Face. The most downloaded are Yi Ko 6B, Yi Ko 6B and Yi Ko 6B. Parameter counts run from 31M to 34.6B, and the longest trained context window is 128K tokens.
A Q4_K_M file of a Richarderkhov model is between 0.0 to 20.8 GB, which is the quant most people start with. Most files come from RichardErkhov (77). The quants you will meet most often are Q2_K (77), Q4_K_S (76), Q4_0 (76) and Q3_K_S (76), where the number is how many models offer that quant.
Frequently asked questions
Which Richarderkhov GGUF should I download?
The most downloaded Richarderkhov GGUF here is Yi Ko 6B. 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 Richarderkhov model need?
Q4_K_M files of Richarderkhov models on this site range from 0.0 to 20.8 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 Richarderkhov GGUF files come from?
The most common quantizers here are RichardErkhov. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.