onprem-ai/Apertus-v1.5-8B-FP8
Quantization vs swiss-ai/Apertus-v1.5-8B. onprem-ai/Apertus-v1.5-8B-FP8 is a quantized version of the other (F8_E4M3/BF16).
Quantization vs swiss-ai/Apertus-v1.5-8B. onprem-ai/Apertus-v1.5-8B-FP8 is a quantized version of the other (F8_E4M3/BF16).