altomek
/

Llama-3.1-Minitron-4B-Width-Base-8bpw-EXL2

8-bit precision

Model card Files Files and versions Community

Edit model card

Llama-3.1-Minitron-4B-Width-Base

ExLlamav2 8 bpw quant of https://huggingface.co/nvidia/Llama-3.1-Minitron-4B-Width-Base

Downloads last month: 7

Inference API

Inference API (serverless) has been turned off for this model.

Model tree for altomek/Llama-3.1-Minitron-4B-Width-Base-8bpw-EXL2

Base model

nvidia/Llama-3.1-Minitron-4B-Width-Base

Quantized

(16)

this model