Field notes

The on-device AI blog

Small language models, Apple Intelligence, private machine learning — explained for humans.

July 7, 2026 · 9 min read

The number "60+ supported models" doesn't mean what you think

Every local-AI app's description carries the same kind of number. Ours vendors an engine that recognizes three Qwen-family architectures — and none of them is the one Qwen's current releases actually use.

July 7, 2026 · 5 min read

We checked two similar 1.5B models this week. Only one would load.

SLM Weekly #1: what we added to the privateSLM catalog, what we skipped, and the exact grep command that told us which was which.

July 3, 2026 · 4 min read

privateSLM 2.0: a chat app that uses the model already inside your phone

Zero-download AI chat via Apple Intelligence, a local GGUF fallback, real chat history and hands-free voice — everything on device.

July 3, 2026 · 6 min read

What is an SLM? Small language models, explained

GPT-class models get the headlines, but the most interesting shift in AI is happening at the small end. Here's why 1–3B parameter models matter.

July 3, 2026 · 7 min read

Apple Intelligence for developers: the Foundation Models framework

iOS 26 gives every app direct access to Apple's on-device model. What it can do, what it can't, and what we learned shipping with it.

July 3, 2026 · 5 min read

Why on-device AI beats the cloud for privacy

"We don't store your data" is a promise. Physics is a guarantee. The case for AI that never phones home.