nvidia/Phi-4-reasoning-plus-FP8
Quantization vs microsoft/Phi-4-reasoning-plus. nvidia/Phi-4-reasoning-plus-FP8 is a quantized version of the other (F8_E4M3/BF16).
Quantization vs microsoft/Phi-4-reasoning-plus. nvidia/Phi-4-reasoning-plus-FP8 is a quantized version of the other (F8_E4M3/BF16).