Claris Harbor: turn your Macs into a private AI inference server
Apple's Claris subsidiary is privately previewing Harbor, a Mac app that runs open-weight models locally on Apple silicon and pools unified memory across Thunderbolt 5 Macs into one inference server.
Why it matters
The easiest on-ramp to local AI Apple has shipped: no command line, no manual setup, and multi-Mac memory pooling for models too big for one machine.
What you could build with it
A small studio with two or three Apple silicon Macs could pool them with Harbor into a private inference server for its own coding and drafting models, keeping client code on its own hardware instead of paying per-token cloud bills.
Does it hold up?
Too early to judge: Harbor is in private preview with no public download, no pricing and no official Apple announcement, so everything rests on a pulled App Store listing and a Claris sign-up page.
Built with Claris Harbor
- Apple's Claris Testing 'Harbor' App for Local AI on Macsmacrumors · Harbor turns Apple silicon Macs into a private AI server, pooling memory over Thunderbolt 5; early access, App Store listing briefly appeared then removed.
- Apple's leaked Harbor app would turn your Mac into a private AI inference serveraifrontierpost · Leak writeup: private preview under Claris, no public download or pricing, features and timing could change before anything ships.
- Apple Harbor App Runs Local AI Across Macs Over Thunderbolt 5ithinkdiff · Harbor pools Thunderbolt 5 Macs' unified memory so a cluster can load models too big for a single Mac; in private preview.
Learn more
First spotted on article: source.
More AI models
VoiceStudio: open-source, fully-local ElevenLabs alternative for voice cloning, dubbing, and audiobooksdebpalash/VoiceStudio is a desktop app that runs voice cloning, voice design, video dubbing, dictation, transcription…models · JEV 0.75Edge0-145B: open 145B MoE that runs on a single consumer GPUEdge0 open-sourced 145B and 120B latent-MoE models derived from Qwen3.8-Flash-Next, plus an inference framework that…models · JEV 0.74Strata: run a 125B model on a gaming PCFree, MIT-licensed local inference engine that runs Qwen3.8-Flash-Next (125B MoE, about 6B active per token) on…models · JEV 0.73Google AI Edge Gallery: offline speech recognition and synthesis on-deviceGoogle added fully offline speech recognition and text-to-speech to AI Edge Gallery, with ML Kit APIs on Android and…models · JEV 0.73Soup: fine-tune an 8B LLM on a 4 GB laptop GPU from one YAML fileAn open-source CLI that fine-tunes LLMs from a single YAML file, with layer streaming that trains an 8B model on a 4…models · JEV 0.73Tencent Hunyuan Hy3: open 295B MoE with 21B active under Apache 2.0Tencent open-sourced Hy3, a 295B-parameter mixture-of-experts model with only 21B parameters active per token, under…models · JEV 0.73
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.