- i am more excited about the ondevice foundation model update that is coming https://developer.apple.com/documentation/updates/foundation... (not much info yet)
but i maintain https://github.com/Arthur-Ficial/apfel so i might be biased
by MysticOracle
0 subcomment
- WWDC 2026 Core AI videos
Meet Core AI - https://developer.apple.com/videos/play/wwdc2026/324/
Dive into Core AI model authoring and optimization -
https://developer.apple.com/videos/play/wwdc2026/325/
Integrate on-device AI models into your app using Core AI -
https://developer.apple.com/videos/play/wwdc2026/326/
by bensyverson
4 subcomments
- Wow, this seems to be a new way to convert PyTorch models to a format that runs across CPU, GPU & Apple's Neural Engine (ANE). [0]
Does this completely replace the previous API, CoreML? [1]
[0]: https://apple.github.io/coreai-optimization/
[1]: https://developer.apple.com/documentation/coreml/
- Free server-size model access for apps with <2M downloads, getting the same privacy guarantees. Hopefully they scale this up to all apps in time (I assume hardware/cost constrained, but larger devs would pay).
https://developer.apple.com/private-cloud-compute/
- AI future is clearly local, and my recent pitch has been "infinite tokens." Because that's what my M1 MBP can do; and that's what my RTX3090 can do. I don't need to pay hundreds of dollars a month and no one else does either.
- they are also working on activations (w4a8, w4a16 from what i know). if they deliver (and a big if), it means that given their market reach, they can dictate the way sub 100b parameter models are trained and served to a large extent, given their major usecase would be on device (macos and not ios for most of them).
- something I haven't seen highlighted anywhere yet, while I find it very interesting, is the distributed inference across Macs (JACCL over Thunderbolt 5), an OpenAI-compatible mlx_lm.server, agentic-on-Mac.
Apple keeps MLX (bring-your-own-weights) separate from Foundation Models / Core AI.
by an0malous
9 subcomments
- This is why the AI companies are rushing to IPO. By the end of next year you’ll be running most of your AI on device. They have no moat, they’ve reached the limits of scaling, most of the magic can be distilled into smaller models, and they know it
- Is there something like this on Linux? For example, if I’m an application developer can I assume GNU Core AI (or whatever it is or would be called) will be there if the kernel is >= some particular version?
- Does it mean I can run whatever I want on ANE? Last time I tried it seemed it could only be used by first party features such as Face ID
by connectsnk
1 subcomments
- Do we know what is the underlying model? Is it a custome model developed by Apple or one of gemma/deepseeks under the hood
Hacker News