NVIDIA AI Releases Nemotron-Labs-Diffusion: A Tri-Mode Language Model with 6× Tokens Per Forward Over Qwen3-8B
MarkTechPost
Read Full Article at MarkTechPost →
Ad Slot — In-Article (728x90)
NVIDIA researchers have released Nemotron-Labs-Diffusion, a language model family that unifies three decoding modes in one architecture. The model supports autoregressive (AR) decoding, diffusion-based parallel decoding, and self-speculation decoding.
It is available in 3B, 8B, and 14B parameter sizes. The family includes base, instruct, and vision-language variants.
This is a summary. For the full story, read the original article at MarkTechPost.
Original source: MarkTechPost