cyankiwi/Instella-MoE-16B-A3B-Think-AWQ-INT4

Quantization vs amd/Instella-MoE-16B-A3B-Think. cyankiwi/Instella-MoE-16B-A3B-Think-AWQ-INT4 is a quantized version of the other (I32/BF16).

On the Hub · Downloads on Model Pulse