espressor/meta-llama.Llama-3.2-3B-Instruct_W4A16

Quantization vs meta-llama/Llama-3.2-3B-Instruct. espressor/meta-llama.Llama-3.2-3B-Instruct_W4A16 is a quantized version of the other (BF16/I32).

On the Hub · Downloads on Model Pulse