NVIDIA · Continuous Diffusion LM
Nemotron-Labs-Sigma
NVIDIA has released Nemotron-Labs-Sigma, 14 open checkpoints at 3B and 8B scale in base, instruct, few-step distilled and self-speculative variants. It is a continuous diffusion language model that denoises text in a learned 16-D embedding space rather than discrete tokens. NVIDIA reports Sigma-8B base averaging 71.16 on its 6-task suite, ahead of NLD-8B at 70.22, and a self-speculative 8B decoding 3.46x faster than autoregressive decoding on average. The weights are on Hugging Face under the NVIDIA Nemotron Open Model License, which the cards describe as ready for commercial use, and the models need a CUDA GPU in bfloat16.
Open the source ↗Similar Language Models releases
- Aion 1.0 Instruct 2.3B
Microsoft Applied Sciences Group (Windows & Devices) · On-device SLM · Week 48, 2026
- Clairic and Clairic-flash
Cloudflare (Workers AI Superintelligence team) · Open Extraction LLM · Week 48, 2026
- GPT-6.2 Astra and Sol
OpenAI · Frontier LLM · Week 48, 2026
- ERNIE 5.5 Flash Preview
Baidu · Agentic MoE coding model · Week 47, 2026
- LLMON: LLM-Native Markup Language (Granite 4.1 LLMON previews)
IBM Granite (ibm-granite) · Structured Prompt Format · Week 47, 2026
- BotPsy-0.8B
Tether AI Research (QVAC) · On-Device Agent LLM · Week 47, 2026
More from NVIDIA
- NVIDIA DAQIRI
NVIDIA · GPU Data Acquisition · Week 48, 2026
- NVIDIA Cosmos Data Factory
NVIDIA · Physical AI data · Week 48, 2026
- Nemotron for Science
NVIDIA · Science Agent Toolkit · Week 48, 2026
- Nemotron RL Litmus-Bench V2.0
NVIDIA · Science Post-Training Dataset · Week 48, 2026
- NVIDIA Vera Rubin NVL72 in MLPerf Training v6.1
NVIDIA · Training Benchmark Results · Week 48, 2026
- NVIDIA Rubin HPC
NVIDIA · HPC GPU for Agents · Week 48, 2026
Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.