Hybrid Compute on Mac ships with open-sourced local inference engine and PII classifier
andrewgwils · x · 2026-09-05
Alongside this week's launch of Hybrid Compute on Mac, Jeremy Yang announced the open-sourcing of two key pieces of the stack: a custom local inference engine and a PII classifier model.
- The local inference engine runs models on-device on Macs, paired with Hybrid Compute for a local + cloud hybrid setup.
- The PII classifier detects and scrubs personally identifiable information before data leaves the device, serving as a privacy layer.
- The architecture — sensitive data stays local, general capability goes to cloud — is a useful reference for on-device AI and privacy-compliant apps.
More from Infra
- llama.cpp team launches Llama: one-click local AI on your Mac menu bar — Hugging Face · 2026-10-23
- China's daily token use hits 500T, up 4x as average price doubles to ¥13.46 — teortaxesTex · 2026-10-23
- New all-reduce kernels deliver 12% decode speedup for DeepSeek-V4.1 on PCIe-connected GPUs — AlpinDale · 2026-10-23
- Offshore oil rigs could be converted into AI data centers powered by stranded gas — clemnt · 2026-10-23
- Same native UI, two stacks: Swift build is ~80MB Mac-only, Zig build is ~10MB cross-platform — jedisct1 · 2026-10-23
- SurfSense: an open-source local NotebookLM with MCP agents and a prompt-caching lesson — FurtiveMirth · 2026-10-23