Edge AI
On-device AI and cloud models are used together. Apple's 2026 design uses both and sends the more demanding work to cloud models. Where a task should run depends on quality, memory, response time, energy use and privacy.
Research snapshot · updated Nov 12, 2026
State of the art (2026)
Phones and PCs now run useful AI models on the device, and send harder tasks to cloud models. Microsoft requires a neural processor rated at 40 TOPS or more for a Copilot+ PC, and its own Surface models list Intel processors rated at 40 or 48 TOPS. TOPS figures are a rough guide only, because they depend on numerical precision and workload. Apple uses both on-device and cloud models and keeps the more demanding work for the cloud. Where a task runs depends on quality, memory, latency, energy use and privacy.
Explore the deeper analysis in CanaryIQ
Explore what is covered below. These previews show the structure; log in to read the full analysis.
Signal stack
Evidence stacked leading → lagging
11 signals
Signal stack
Evidence stacked leading → lagging
Technology-native KPIs
Metrics that predict trajectory, tracked over time
4 tracked
Technology-native KPIs
Metrics that predict trajectory, tracked over time
Landscape map
Who builds what, and who depends on whom
87 players · 6 layers
Landscape map
Who builds what, and who depends on whom
Catalyst calendar
Dated events that will move the position
7 ahead
Catalyst calendar
Dated events that will move the position
Technology roadmap
Milestones on the path to maturity
8 milestones
Technology roadmap
Milestones on the path to maturity
Watchlists
Companies, people and papers, each with a condition for removing it
20 · 20
Watchlists
Companies, people and papers, each with a condition for removing it
Decision frameworks
What our view means for your job
Locked
Decision frameworks
What our view means for your job
Thesis changelog
When our view changed, and why
8 updates
Thesis changelog
When our view changed, and why
Change our mind
2 disconfirming conditions
You've read the verdict. The file is much deeper.
The full signal stack, technology-native KPIs tracked over time, the landscape of who depends on whom, the dated catalyst calendar, decision frameworks for every desk, live watchlists and a record of every time our view on Edge AI has changed. All of it is in CanaryIQ.