kosbu
/

Llama-3.3-70B-Instruct-AWQ

Text Generation

text-generation-inference

4-bit precision

Model card Files Files and versions

Llama-3.3-70B-Instruct AWQ 4-Bit Quantized Version

This repository provides the AWQ 4-bit quantized version of meta-llama/Llama-3.3-70B-Instruct, originally developed by Meta AI.

Downloads last month: 487,660

Safetensors

Model size

71B params

Tensor type

I32

·

F16

·

Model tree for kosbu/Llama-3.3-70B-Instruct-AWQ

Base model

meta-llama/Llama-3.1-70B

Finetuned

meta-llama/Llama-3.3-70B-Instruct

Quantized

(139)

this model

Space using kosbu/Llama-3.3-70B-Instruct-AWQ 1