RedHatAI/Apertus-70B-Instruct-2509-FP8-dynamic

Quantization vs swiss-ai/Apertus-70B-Instruct-2509. RedHatAI/Apertus-70B-Instruct-2509-FP8-dynamic is a quantized version of the other (F8_E4M3/BF16).

On the Hub · Downloads on Model Pulse