nvidia/llama-nemotron-embed-vl-1b-v2-fp8

Quantization vs nvidia/llama-nemotron-embed-vl-1b-v2. nvidia/llama-nemotron-embed-vl-1b-v2-fp8 is a quantized version of the other (BF16/F8_E4M3).

On the Hub · Downloads on Model Pulse