jnjj
/

gemma-3-1b-it-qat-int4-quantized-inference-unrestricted-pruned-weights-only-sf

4-bit precision

Model card Files Files and versions

No model card

Downloads last month: 1

Safetensors

Model size

1.0B params

Tensor type

BF16

·

Inference Providers NEW

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