Concern 446 · Working draft · editorial review in progress
On-device inference limits
On-device inference limits are the practical constraints of running AI directly on a phone or computer rather than a remote server.
Understanding the concern
Local processing can keep some information off a provider's servers and work without a network connection. But device memory, battery, heat and available computing power shape which models and tasks fit. A system may use a smaller model or switch some requests to a server, creating a privacy boundary users need to understand.
The comparison is like carrying a toolkit versus sending work to a large workshop. The portable kit can be exactly right for many jobs. It is inaccurate to say local AI is always worse, just as cloud use is not automatically necessary. Capability changes over time, so testing should focus on the user's actual task and device.
An example
A feature handles short requests locally but sends more demanding ones to a server without making the change clear.
Illustrative unless identified as a documented case.
Words in plain English
- AI
- Software that learns patterns from examples or uses rules to perform tasks such as recognizing images or generating text. It can make mistakes and does not understand every situation as a person would.
- Model
- The learned part of an AI system. It uses patterns found during training to produce an answer or prediction.
- Inference
- Drawing a conclusion from clues. In AI engineering it can also mean running a trained model to produce an output.
Evidence and its limits
Apple's report describes one vendor's 2025 design. It is not a permanent limit on mobile AI or a universal comparison with cloud models.
Apple Machine Learning Research · First-party technical report
Updates to Apple's On-Device and Server Foundation Language Models ↗ (opens in a new tab)2025 design choices for local and server models; not an independent ranking or permanent limit on mobile capability.
Broader frameworks and background
These resources provide context. They do not establish every claim in this concern.
- OECD AI Principles (opens in a new tab)
framework
- NIST AI RMF (opens in a new tab)
framework
A question to discuss
Which tasks stay on the device, and does the user know when data leaves it?
Keep track of different views, what needs checking, and any next step in your own discussion notes.
Open discussion notes →Principles for the conversation
Before you finish · reflect together
Virtues and principles to consider
Virtues are qualities we practice in how we treat people and make choices. They are not scores for judging someone. Use these ideas to explore what a thoughtful response could look like.
Dignity
Dignity means recognizing each person's worth regardless of usefulness, status, or a system's score. People deserve respect and a voice in matters that affect them.
Explain important decisions, avoid humiliating treatment, and keep room for a person's story. Do not treat a prediction as a complete account of who someone is.
Ask together: Does this use treat each person as someone whose experience matters?
Trustworthiness
Trustworthiness means giving people good reasons to rely on you. It grows when promises, actions, and evidence line up. With AI, a friendly voice or a famous brand is not enough: people need to know what was checked and what could still go wrong.
In practice, keep promises small enough to test, record mistakes, and tell people when the tool's limits affect them. If a service promises human review, make sure a person really has time and authority to review it.
Ask together: What would give the people affected a sound reason to trust this use?
Stewardship
Stewardship means caring for resources and systems that others depend on, including people who will use them later. It looks beyond the benefit of a quick launch.
Plan for maintenance, energy use, data protection, and eventual shutdown. Ask who will look after the tool when the original team moves on and how future users can avoid inheriting hidden costs.
Ask together: What are we responsible for caring for over time?
Editorial ratings
These are editorial judgments from the register, not measured probabilities or predictions about your situation.
About the register and scoring →More ways to explore
Search for more writing
For more specific or recent material, open a search below or ask for a web summary. AI-generated summaries can contain mistakes; open the original articles to check them.