Vistral-24B-Instruct (AWQ Quantized)

Описание

Это квантизированная версия модели Vikhrmodels/Vistral-24B-Instruct.

  • Базовая модель: Vistral-24B-Instruct
  • Метод квантизации: AWQ (4-bit)
Downloads last month
89
Safetensors
Model size
4B params
Tensor type
I64
·
I32
·
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Chewye/Vistral-24B-Instruct-AWQ