Openchat GGUF models
128 GGUF models in the Openchat family, quantized by 40 uploaders. Sizes run from 7M to 13B parameters. The longest trained context is 128K tokens.
About the Openchat GGUF models
Openchat is represented on ggufmodels.com by 128 GGUF models, quantized by 40 uploaders on Hugging Face. The most downloaded are openchat-3.6-8b-20240522, openchat_openchat-3.5-1210 and openchat_openchat_3.5. Parameter counts run from 7M to 13B, and the longest trained context window is 128K tokens.
A Q4_K_M file of a Openchat model is between 4.4 to 7.9 GB, which is the quant most people start with. Most files come from mradermacher (43), RichardErkhov (11) and tensorblock (10). The quants you will meet most often are Q4_K_M (96), Q2_K (95), Q5_K_M (89) and Q6_K (86), where the number is how many models offer that quant.
Frequently asked questions
Which Openchat GGUF should I download?
The most downloaded Openchat GGUF here is openchat-3.6-8b-20240522. 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 Openchat model need?
Q4_K_M files of Openchat models on this site range from 4.4 to 7.9 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 Openchat GGUF files come from?
The most common quantizers here are mradermacher, RichardErkhov 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.