Nemotron Labs Diffusion 8B Base
NVIDIA's Nemotron Labs Diffusion 8B Base is a tri-mode language model that excels at efficient text generation, supporting both autoregressive decoding and diffusion-based parallel decoding. With a focus on decode efficiency, it achieves high acceptance lengths and decoding speed, notably 2.7x faster than autoregressive decoding on the DGX Spark platform.
Input
Output
Context
4K
Max Output
-
Parameters
8.5B
Technical Specifications
Model TypeChat
Context Window4,096 tokens
Max Output TokensNot available
Parameters8.5B
Release DateJan 14, 2026
Training CutoffNot available
Licenseother
Open SourceYes
Input Modalities
Text
Output Modalities
Text
Capabilities
Resources & Links
Estimated GPU Requirements for Nemotron Labs Diffusion 8B Base
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 23, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.