Kimi GGUF models
439 GGUF models in the Kimi family, quantized by 120 uploaders. Sizes run from 2M to 5376B parameters. The longest trained context is 1024K tokens.
About the Kimi GGUF models
Kimi is represented on ggufmodels.com by 439 GGUF models, quantized by 120 uploaders on Hugging Face. The most downloaded are Kimi-K3, Kimi-K2.7-Code and Kimi Linear 48B A3B Instruct. Parameter counts run from 2M to 5376B, and the longest trained context window is 1024K tokens.
A Q4_K_M file of a Kimi model is between 0.1 to 624.0 GB, which is the quant most people start with. Most files come from Thireus (185), mradermacher (59) and DevQuasar (15). The quants you will meet most often are Q2_K (127), Q4_K_M (123), Q3_K_M (116) and Q6_K (107), where the number is how many models offer that quant.
Frequently asked questions
Which Kimi GGUF should I download?
The most downloaded Kimi GGUF here is Kimi-K3. 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 Kimi model need?
Q4_K_M files of Kimi models on this site range from 0.1 to 624.0 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 Kimi GGUF files come from?
The most common quantizers here are Thireus, mradermacher and DevQuasar. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.