RedHatAI/Llama-3.2-3B-Instruct-FP8
Quantization vs meta-llama/Llama-3.2-3B-Instruct. RedHatAI/Llama-3.2-3B-Instruct-FP8 is a quantized version of the other (F8_E4M3/BF16).
Quantization vs meta-llama/Llama-3.2-3B-Instruct. RedHatAI/Llama-3.2-3B-Instruct-FP8 is a quantized version of the other (F8_E4M3/BF16).