Chat GGUF models
88 GGUF models in the Chat family, quantized by 31 uploaders. Sizes run from 121M to 65.3B parameters. The longest trained context is 256K tokens.
About the Chat GGUF models
Chat is represented on ggufmodels.com by 88 GGUF models, quantized by 31 uploaders on Hugging Face. The most downloaded are CarbonGPT, Chat_Noir and Chat_Noir 24b v2. Parameter counts run from 121M to 65.3B, and the longest trained context window is 256K tokens.
A Q4_K_M file of a Chat model is between 0.1 to 39.3 GB, which is the quant most people start with. Most files come from mradermacher (39), luckycanucky (6) and RichardErkhov (4). The quants you will meet most often are Q4_K_M (62), Q2_K (59), Q5_K_M (57) and Q3_K_M (55), where the number is how many models offer that quant.
Frequently asked questions
Which Chat GGUF should I download?
The most downloaded Chat GGUF here is CarbonGPT. 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 Chat model need?
Q4_K_M files of Chat models on this site range from 0.1 to 39.3 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 Chat GGUF files come from?
The most common quantizers here are mradermacher, luckycanucky and 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.