AI brief
At IFA 2026, NVIDIA and Microsoft said they are working together to provide faster inference and new tools for running agents locally on NVIDIA hardware, alongside new compact RTX Spark Windows PCs.
Why it matters: It points to a push to let AI agents run on local hardware rather than in the cloud.
Written by AI from NVIDIA Blog's published text.
Background
From our own funding, model and news trackers, not from the source.
Microsoft
- Newest model on the API
- Phi 4 · 10 Jan 2025 · $0.07 in / $0.14 out per million tokens
- Last 30 days
- 58 news stories
NVIDIA
- Newest model on the API
- Nemotron 3.5 Super VL · 15 Oct 2026 · $0.15 in / $0.5 out per million tokens
- Last 30 days
- 67 news stories
Source
“Frontier intelligence is going local. At IFA 2026, NVIDIA, Microsoft and its partners are teaming up to provide faster inference and new tools that make agents easier to set up and run locally on NVIDIA hardware.”
Published by the organisation it describes; treat claims as first-party statements.
Read original story ↗