Models · FRESH UPDATE · SINGLE SOURCE · 1 source
Nvidia's Nemotron 3.5 Super VL is an open model built to run enterprise AI agents nonstop
In shortAlongside Nemotron 3.5 Super VL, NVIDIA is releasing open datasets on Hugging Face.
Based on reporting from NVIDIA; no matching primary source is listed in the Source Stack yet.
What happened
Organizations can adapt and deploy the model’s open weights in supported local, data center, or cloud environments to meet their infrastructure and data requirements. Inference cost for this workload will decrease by 40x and latency by 5x.
What the report says
- Alongside Nemotron 3.5 Super VL, NVIDIA is releasing open datasets on Hugging Face.
This Live Update contains 3 concrete source-backed facts. SourceVane will add impact analysis only after it is supported.
Living trackers
Follow this signal
Related signals
- Run fast, private agents on-device with LFM2.5-24B-A2B
Mid-training then adds 2T tokens at 32K context, weighted toward reasoning, math, code, instruction following, and multilingual text, and 300B tokens at 131K context, weighted toward long-context data. LFM2.5-24B-A2B ships with day-one support across the inference ecosystem, including llama.cpp, MLX, vLLM, SGLang, and ONNX.
- Build Local AI Apps with C++ and NVIDIA TensorRT RTX Samples
For preprocessing and postprocessing around exported model inference, the FLUX.2 sample uses ONNX Runtime’s graphics interop capability, introduced in version 1.25, with Vulkan and DirectX for sampling. DirectX is available only on Windows. Adding AI models to local applications requires a portable model format, a reliable runtime, and acceleration that works across target systems.
- Know Who Spoke When: Build Real-Time, Multi-Speaker AI with NVIDIA Nemotron 3 Diarization
Nemotron 3 Diarization expands support to eight speakers and improves the accuracy and throughput measured in the following evaluations. More right context can help the model interpret speaker transitions, while less right context reduces the time it must wait before producing a result.
