Koushik-06
/

sarvam-30b-nvfp4

8-bit precision

Model card Files Files and versions

sarvam-30B-nvfp4

This is the quantized NVFP4 version of the Sarvam 30B model.

Downloads last month: 5

Safetensors

Model size

17B params

Tensor type

BF16

·

F32

·

F8_E4M3

·

U8

·

Inference Providers NEW

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