Chocolatine GGUF models
96 GGUF models in the Chocolatine family, quantized by 19 uploaders. Sizes run from 3.82B to 78B parameters. The longest trained context is 256K tokens.
About the Chocolatine GGUF models
Chocolatine is represented on ggufmodels.com by 96 GGUF models, quantized by 19 uploaders on Hugging Face. The most downloaded are Chocolatine 14B Instruct DPO v1.2 i1, Chocolatine 3B Instruct DPO v1.2 and Chocolatine 3B Instruct DPO Revised Q4 K M. Parameter counts run from 3.82B to 78B, and the longest trained context window is 256K tokens.
A Q4_K_M file of a Chocolatine model is between 2.3 to 19.9 GB, which is the quant most people start with. Most files come from mradermacher (57), jpacifico (8) and tensorblock (6). The quants you will meet most often are Q4_K_M (75), Q2_K (74), Q3_K_M (70) and Q4_K_S (68), where the number is how many models offer that quant.
Frequently asked questions
Which Chocolatine GGUF should I download?
The most downloaded Chocolatine GGUF here is Chocolatine 14B Instruct DPO v1.2 i1. 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 Chocolatine model need?
Q4_K_M files of Chocolatine models on this site range from 2.3 to 19.9 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 Chocolatine GGUF files come from?
The most common quantizers here are mradermacher, jpacifico 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.