Apple Core AI Framework
hmokiguess
248 points
60 comments
June 08, 2026
Related Discussions
Found 5 related stories in 114.3ms across 10,002 title embeddings via pgvector HNSW
- Siri AI 0xedb · 510 pts · June 08, 2026 · 61% similar
- Apple reveals new AI architecture built around Google Gemini models unclefuzzy · 486 pts · June 08, 2026 · 59% similar
- Launch HN: RunAnywhere (YC W26) – Faster AI Inference on Apple Silicon sanchitmonga22 · 199 pts · March 10, 2026 · 59% similar
- Show HN: Apfel – The free AI already on your Mac franze · 660 pts · April 03, 2026 · 56% similar
- AI (2014) bjornroberg · 69 pts · March 20, 2026 · 56% similar
Discussion Highlights (10 comments)
bensyverson
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/
MysticOracle
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/
franze
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
an0malous
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
criddell
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?
dvt
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.
connectsnk
Do we know what is the underlying model? Is it a custome model developed by Apple or one of gemma/deepseeks under the hood
ankit219
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).
scosman
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/
JV00
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