Calme GGUF models
104 GGUF models in the Calme family, quantized by 12 uploaders. Sizes run from 3.09B to 78B parameters. The longest trained context is 128K tokens.
About the Calme GGUF models
Calme is represented on ggufmodels.com by 104 GGUF models, quantized by 12 uploaders on Hugging Face. The most downloaded are calme-2.3-legalkit-8b, Calme-7B-Instruct-v0.9 and Calme 7B Instruct v0.3. Parameter counts run from 3.09B to 78B, and the longest trained context window is 128K tokens.
A Q4_K_M file of a Calme model is between 1.9 to 50.7 GB, which is the quant most people start with. Most files come from mradermacher (57), MaziyarPanahi (19) and RichardErkhov (11). The quants you will meet most often are Q2_K (100), Q4_K_S (94), Q3_K_M (91) and Q3_K_L (90), where the number is how many models offer that quant.
Frequently asked questions
Which Calme GGUF should I download?
The most downloaded Calme GGUF here is calme-2.3-legalkit-8b. 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 Calme model need?
Q4_K_M files of Calme models on this site range from 1.9 to 50.7 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 Calme GGUF files come from?
The most common quantizers here are mradermacher, MaziyarPanahi 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.