NVIDIA Releases Nemotron 3.5 Super VL, a 120B Open Multimodal Agent Model
Quick Answer
NVIDIA has launched the Nemotron 3.5 Super VL, a 120 billion-parameter multimodal model featuring 12 billion active parameters and a 1 million-token context.
Quick Take
This model operates on a single DGX Spark and includes two Bolt edge models, utilizing NVFP4 weights for enhanced performance.
Key Points
- Nemotron 3.5 Super VL has 120B total parameters with 12B active ones.
- The model supports a context length of 1 million tokens.
- It runs on a single DGX Spark system.
- Includes two additional Bolt edge models for enhanced functionality.
- Utilizes NVFP4 weights for optimized performance.
Article Excerpt
From source RSS / original summaryNVIDIA released Nemotron 3. 5 Super VL, an open 120B-parameter multimodal MoE model with 12B active parameters, 1M-token context and NVFP4 weights that run on 1 DGX Spark, plus 2 Bolt edge models. The post NVIDIA Releases Nemotron 3. 5 Super VL, a 120B Open Multimodal Agent Model appeared first on MarkTechPost.
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from MarkTechPost
See more →Microsoft AI Releases Microsoft-Decision-1: A Qwen3.5-9B Decision-Scoring Model
Microsoft has launched Microsoft-Decision-1, a decision-scoring model derived from Alibaba's Qwen3.5-9B. This model focuses on routing, classification, verification, and agent control, providing calibrated probabilities for fixed answer options instead of generating text. It is now available in Microsoft Foundry and OpenRouter.