Nemotron-Labs-Diffusion 8B
Nemotron-Labs-Diffusion 8B is a released long context model with open-weight and 128K context; evaluate it while provider pricing coverage matures.
- Family
- Nemotron-Labs-Diffusion
- Released
- 2026-05-23
- Context
- 128K
- Parameters
- 8B
- Architecture
- Decoder Only
- Specialization
- general
- Openness
- Open weights
- License
- NVIDIA Open ModelPermitted
- Weights
- Available
- Code
- Unknown
- Training
- Pretrained
No tracked provider pricing is available yet.
About
NVIDIA Nemotron-Labs-Diffusion 8B is the mid-size instruct model in NVIDIA Research's diffusion language model family, released May 23, 2026. Achieves 2.6× higher tokens per forward pass than autoregressive models in diffusion mode and 1.2% improved average accuracy over Qwen3 8B. Like all DLMs in this family, it supports three decoding modes: autoregressive, diffusion (block-by-block parallel), and self-speculation. Trained on 1.3T tokens from NVIDIA Nemotron datasets plus 45B fine-tuning tokens. Released under NVIDIA Nemotron Open Model License. Available on Hugging Face at nvidia/Nemotron-Labs-Diffusion-8B.
Providers
No active provider routes are tracked for this model yet.
Capabilities
No model capability flags are currently sourced.
Benchmark peer barsfor Long context
No task-mapped benchmark peers are available for this model yet.
Migration checks
No linked migration route is available for this model yet.
Comparison and alternatives
Browse all comparisons →No tracked provider pricing is available yet.