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
5
Safetensors
Model size
6B params
Tensor type
F16
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
(125)
this model