Nemotron-Labs-Diffusion Models by NVIDIA AI

NVIDIA AINVIDIA Open ModelOpen weights

3 models2026Up to 131k ctx

Last refreshed 2026-06-20. Next refresh: weekly.

Details

ResearcherNVIDIA AI

LicenseNVIDIA Open Model

Commercial useCommercial use: permitted

Models3

Released2026

Max context131k

Links

Website HuggingFace

About

NVIDIA Nemotron-Labs-Diffusion is a family of diffusion language models (DLMs) released by NVIDIA Research in May 2026. Unlike traditional autoregressive models, they generate text by producing multiple tokens in parallel and iteratively refining them, enabling up to 6× throughput over comparable AR models. Available in 3B, 8B, and 14B sizes with base and instruct variants; an 8B VLM is also included.

Decision facts

Best fit: coding
Capability starting point: Nemotron-Labs-Diffusion 3B with 131k context
Lowest tracked input: Not tracked
Closest related family: NVIDIA Nemotron Nano 12B v2 VL

Current Variants

Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.

3 in view

Nemotron-Labs-Diffusion 3BCurrent

Use when the workload needs 131k context and 3B parameters.

2026-05131k context3B parameters

Nemotron-Labs-Diffusion 8BCurrent

Use when the workload needs 131k context and 8B parameters.

2026-05131k context8B parameters

Nemotron-Labs-Diffusion 14BCurrent

Use when the workload needs 131k context, 14B parameters, and fine tuning.

2026-05131k context14B parametersfine tuning

Current Nemotron-Labs-Diffusion variants with use-when guidance and lifecycle status
Model	Use when	Released	Signals	Status
Nemotron-Labs-Diffusion 3B	Use when the workload needs 131k context and 3B parameters.	2026-05	131k context3B parameters	Current
Nemotron-Labs-Diffusion 8B	Use when the workload needs 131k context and 8B parameters.	2026-05	131k context8B parameters	Current
Nemotron-Labs-Diffusion 14B	Use when the workload needs 131k context, 14B parameters, and fine tuning.	2026-05	131k context14B parametersfine tuning	Current