Model Releases
What makes NVIDIA Nemotron 3.5 Super VL different? → Text, image, document, and video understanding in one model → Reasoning and tool use wi…
What makes NVIDIA Nemotron 3.5 Super VL different? → Text, image, document, and video understanding in one model → Reasoning and tool use with visual context preserved across steps → 120B hybrid MoE (
What makes NVIDIA Nemotron 3.5 Super VL different? → Text, image, document, and video understanding in one model → Reasoning and tool use with visual context preserved across steps → 120B hybrid MoE (12B active) → Multi-token prediction for faster generation → NVFP4 KV cache for more concurrent long-context sessions → Open-weights for customization and post-training
Related
- .@NVIDIA Nemotron 3.5 Super VL is now live on Together AI. An open-weight multimodal model built for visual reasoning and always-on agents t…
- @nvidia Run Nemotron 3.5 Super VL on Together AI Start building: https://www.together.ai/models/nemotron-3-5-super-vl
Source: Together AI (X) | 2026-10-15