EXL3 quantization of gemma-3-12b-it, 6 bits per weight.

HumanEval (argmax)

Model Q4 Q6 Q8 FP16
gemma-3-12b-it-exl3-4bpw 82.9 82.9 83.5 83.5
gemma-3-12b-it-exl3-6bpw 83.5 81.7 82.3 82.3
Downloads last month
14
Safetensors
Model size
5.85B params
Tensor type
FP16
I16
BF16
Inference Providers NEW
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support

Model tree for isogen/gemma-3-12b-it-exl3-6bpw

Quantized
(88)
this model