fifrio
/

gemma-3-4b-it-gptq-4bit-calibration-Swahili-128samples

4-bit precision

Model card Files Files and versions

No model card

Downloads last month: 80

Safetensors

Model size

4B params

Tensor type

I32

·

BF16

·

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support