Towards Speed-of-Light Text Generation with Nemotron-Labs Diffusion Language Models
NVIDIA's Nemotron-Labs Diffusion models generate multiple tokens in parallel and iteratively refine them, breaking the autoregressive token-by-token bottleneck. The family includes 3B, 8B, and 14B text models plus an 8B vision-language model, all released under permissive licenses with training code.