RedHatAI/Llama-3.2-1B-Instruct-FP8
Quantization vs meta-llama/Llama-3.2-1B-Instruct. RedHatAI/Llama-3.2-1B-Instruct-FP8 is a quantized version of the other (BF16/F8_E4M3).
Quantization vs meta-llama/Llama-3.2-1B-Instruct. RedHatAI/Llama-3.2-1B-Instruct-FP8 is a quantized version of the other (BF16/F8_E4M3).