shadowrock-io/Nemotron-3-Embed-8B-Community-FP8
Quantization vs nvidia/Nemotron-3-Embed-8B-BF16. shadowrock-io/Nemotron-3-Embed-8B-Community-FP8 is a quantized version of the other (F8_E4M3/BF16).
Quantization vs nvidia/Nemotron-3-Embed-8B-BF16. shadowrock-io/Nemotron-3-Embed-8B-Community-FP8 is a quantized version of the other (F8_E4M3/BF16).