amd/Llama-3.1-8B-Instruct-w4a16-asym-torchao-v0.17.0

Quantization vs meta-llama/Llama-3.1-8B-Instruct. amd/Llama-3.1-8B-Instruct-w4a16-asym-torchao-v0.17.0 is a quantized version of the other (U8/BF16).

On the Hub · Downloads on Model Pulse