On-device models vs cloud APIs: Cost and latency from a real iOS app
Real usage economics and latency behavior.
On-Device AICloud APICost Analysis
Read article
Writing
On-device vs Cloud
Trade-offs between local model execution and cloud inference APIs in consumer apps.
Prompt engineering for 2B models: Think like a compiler
Why structure wins for smaller local models.
Prompt EngineeringSmall Models
Read article