cyankiwi/Llama-3_3-Nemotron-Super-49B-v1_5-AWQ-4bit
Quantization vs nvidia/Llama-3_3-Nemotron-Super-49B-v1_5. cyankiwi/Llama-3_3-Nemotron-Super-49B-v1_5-AWQ-4bit is a quantized version of the other (I32/BF16).
Quantization vs nvidia/Llama-3_3-Nemotron-Super-49B-v1_5. cyankiwi/Llama-3_3-Nemotron-Super-49B-v1_5-AWQ-4bit is a quantized version of the other (I32/BF16).