btbtyler09
/

Llama-3.3-70B-Instruct-gptq-8bit

Text Generation

8-bit precision

Model card Files Files and versions Community

Work in progress gptq quantization of Llama-3.3.

Downloads last month: 20

Safetensors

Model size

19.9B params

Tensor type

F16

·

I32

·