kalle07/Jan-v1-2509_128_4_autoround

This model is a gguf q4km format of janhq/Jan-v1-2509 generated by intel/auto-round algorithm. Embedding layer and lm-head layer are fallback to 8 bits and non expert layers are fallback to 4 bits
original model:
https://huggingface.co/janhq/Jan-v1-2509

quant_methode:
https://github.com/intel/auto-round

untested...