brunopio
/

gemma-2-2b-it-nbits4-GS64-Axis1-HQQ-T

8-bit precision

Model card Files Files and versions Community

Use the latest transformers for this model.

Downloads last month: 3

Safetensors

Model size

1.67B params

Tensor type

I64

·

FP16

·

U8

·

Inference Providers NEW

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

Model tree for brunopio/gemma-2-2b-it-nbits4-GS64-Axis1-HQQ-T

Base model

google/gemma-2-2b

Finetuned

google/gemma-2-2b-it

Quantized

(159)

this model