NVIDIA Nemotron 3.5 Super VL arrives in SageMaker JumpStart: 120B total and 12B active parameters, a 1M-token context, and an NVFP4 variant of about 75 GB
An open vision-language model aimed at document intelligence and computer-use agents, now a few steps to deploy on AWS. Its specs and the two deployment variants.
// Key points
- It takes image, video and text in and produces text; the language backbone interleaves Mamba-2 and MoE layers (512 routed experts, 22 active per token), includes an MTP head for speculative decoding, and is licensed under OpenMDW 1.1.
- JumpStart offers two variants: NVFP4 at about 75 GB, defaulting to ml.g7.24xlarge, and BF16 at about 249 GB on ml.p5en.48xlarge.
- In AWS's test, the BF16 variant averaged 140.85 output tokens per second per request, and time to first token stayed around half a second across all three configurations.
- NVIDIA positions it for document intelligence, GUI understanding for computer-use agents, video question answering and multimodal agentic applications.
Builder's takeLike Kimi K3.1 Pro landing on Bedrock on 11-08, large open models keep reaching cloud catalogs faster. For scans and screenshots in the AI Cloud Drive, I would compare the NVFP4 variant against the current closed model on my own samples for accuracy and cost per page before moving any traffic.
// Background · from #Open models
Full timeline →- Nov 10 Amazon's HOPE prunes MoE experts by modeling how they work in pairs, ranking 1.58 on average at 50% pruning versus 2.42 for the next-best method, REAP
- Nov 9 Ai2 opens ToyBlocks, a robot learning framework: 85,336 long-horizon demonstrations, about 1,600 hours of data, and up to 24x real-time generation on one GPU
- Nov 8 Kimi K3.1 Pro (Highspeed) arrives on Amazon Bedrock: open-weight, natively multimodal, a 1-million-token context, and explicit prompt caching