Exaone GGUF models
233 GGUF models in the Exaone family, quantized by 74 uploaders. Sizes run from 1.28B to 749B parameters. The longest trained context is 256K tokens.
About the Exaone GGUF models
Exaone is represented on ggufmodels.com by 233 GGUF models, quantized by 74 uploaders on Hugging Face. The most downloaded are EXAONE-4.0-1.2B, EXAONE-4.5-33B and EXAONE-4.0-32B. Parameter counts run from 1.28B to 749B, and the longest trained context window is 256K tokens.
A Q4_K_M file of a Exaone model is between 0.8 to 143.5 GB, which is the quant most people start with. Most files come from mradermacher (67), bartowski (10) and LGAI-EXAONE (10). The quants you will meet most often are Q4_K_M (177), Q8_0 (146), Q6_K (144) and Q5_K_M (143), where the number is how many models offer that quant.
Frequently asked questions
Which Exaone GGUF should I download?
The most downloaded Exaone GGUF here is EXAONE-4.0-1.2B. 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 Exaone model need?
Q4_K_M files of Exaone models on this site range from 0.8 to 143.5 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 Exaone GGUF files come from?
The most common quantizers here are mradermacher, bartowski and LGAI-EXAONE. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.