Apple reportedly building Harbor app to turn Macs into private AI inference servers with Thunderbolt 5 clustering
BenBajarin · x · 2026-11-11
A leaked look at Harbor, an Apple app in development that turns Macs into private AI inference servers: run open-weight models locally on Apple silicon with data never leaving the hardware.
- Memory pooling: connect multiple Macs over Thunderbolt 5; Harbor auto-detects devices and pools unified memory for larger models and higher concurrency.
- Zero setup: plug in, start, and run — no command line or infrastructure expertise needed.
- Built-in model browser: download and load open-weight models in-app.
Commenters note major implications for Apple in the enterprise, positioning the Mac as an AI inference box.
More from Infra
- SpaceX locks 100+ GW of solar cell equipment from SINGULUS for Starmind AI satellites — ns123abc · 2026-11-11
- CoreWeave upgrades to CNCF Platinum member, runs its GPU cloud entirely on Kubernetes — altryne · 2026-11-11
- SpaceX teams with Qualcomm to build AI-native base stations, eyeing first AI carrier — elonmusk · 2026-11-11
- Prism capability extraction: specialists carved from Qwen 27B at <20% memory match full model — tokenbender · 2026-11-11
- Agent Arena: Gemini 4 Carbon Gets More Cost-Competitive as Tasks Get Harder — rseroter · 2026-11-11
- AMD Zen 6 deep dive: cheaper branch mispredicts and a return to Zen 3/4 integer scheduling — jedisct1 · 2026-11-11