Skip to content
AI News HubLIVE
Summary only

NVIDIA AI Releases Nemotron-Labs-Diffusion: A Tri-Mode Language Model with 6× Tokens Per Forward Over Qwen3-8B

NVIDIA researchers have released Nemotron-Labs-Diffusion, a language model family that unifies three decoding modes in one architecture: autoregressive (AR) decoding, diffusion-based parallel decoding, and self-speculation decoding. Available in 3B, 8B, and 14B parameter sizes with base, instruct, and vision-language variants. Self-speculation mode achieves up to 6× tokens per forward over Qwen3-8B while maintaining competitive accuracy. The model is open-source and supports flexible deployment across different concurrency scenarios.

SourceMarkTechPostAuthor: Asif Razzaq
NVIDIA AI Releases Nemotron-Labs-Diffusion: A Tri-Mode Language Model with 6× Tokens Per Forward Over Qwen3-8B
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions

Summary only

Under the source content permission, this page provides an editorial summary, key points, and a link to the original article.

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • Nemotron-Labs-Diffusion integrates AR, diffusion, and self-speculation decoding in a single model with no architectural changes. Switching modes is done at inference time by changing attention patterns.
  • At 8B scale, linear self-speculation delivers 5.99× tokens per forward with 62.81% accuracy, outperforming Qwen3-8B in throughput and accuracy.
  • Training uses a joint AR-diffusion objective with α=0.3, two-stage training on 1.3T tokens, initialized from Ministral3 and trained on 256 NVIDIA H100 GPUs.
  • Open-source release on Hugging Face with simple API for all three modes; requires transformers≥5.0.0 and trust_remote_code=True.

Highlights and analysis are generated automatically and may contain errors. Check the original source.

More recent stories on this topic · Models