- Nemotron 3.5 Super VL, a 120B‑parameter vision‑language model, is now available on Amazon SageMaker JumpStart.
- Supports multimodal inputs (image, video, text) with up to 1 M token context, multi‑token speculative decoding, and ten languages.
- Provides two deployment variants: optimized inference on G7 instances (NVFP4) and BF16 reference weights for fine‑tuning on ml.p5en.48xlarge.