NVIDIA Nemotron 3.5 Super VL arrives on SageMaker JumpStart
First seen Nov 9 Updated Nov 10, 16:12 UTC Heat 20 high evidence
AWS says NVIDIA Nemotron 3.5 Super VL is now available in SageMaker JumpStart. It takes images, video and text as input and outputs text. Reasoning can be configured per request.
- What to do
- Deploy it from SageMaker Studio or with the SageMaker Python SDK.
- Who should care
- Developers building document, computer-use or video agents on AWS.
Why it matters: Developers can deploy a 120B-parameter vision-language model with 1M-token context from SageMaker Studio or the Python SDK.
Key facts
- 120B parameters, 12B active per token (hybrid MoE)
- Context up to 1 million tokens
- Two variants
- NVFP4 and BF16
Timeline
Official
-
NVIDIA Nemotron 3.5 Super VL is now available in Amazon SageMaker JumpStartaws.amazon.com ยท Amazon
Evidence
High evidence: the claim comes from an official source (the company or project itself), or at least two independent sites reported it.
Details written Nov 10, 16:11 UTC from the sources listed above.