@rxwei

AI frameworks at Apple

 San Francisco, CA
Joined September 2009
  • Tweets576
  • Following334
  • Followers5.1K
33Media
💯
Peter Friese
@peterfriese
Sep 21
Replying to @peterfriese
Jev is typesafe, so it's only natural to map Swift types directly to Jev decision primitives:
40
5,454
Richard Wei retweeted
Peter Friese
@peterfriese
Sep 21
Want to use @typesafeai's Jev in your @SwiftLang apps using the convenience of Apple's Foundation Models framework? Well - here you go (GitHub repo link in the replies)! (h/t to @rxwei for the inspiration!)
5
16
1
127
6,833
Jev is a fantastic example of co-designing SDKs and models to unlock a new paradigm! When we were designing the Swift API for Apple’s Foundation Models framework two years ago, we wanted to make type-safe structured responses the standard for apps on our platform. That is why we created the `@​Generable` API, making constrained decoding approachable to app developers. This effectively eliminated structural hallucinations in both tool call arguments and responses, which were especially important for a small on-device model. developer.apple.com/document… It would be fascinating to see decision models conform to the `LanguageModel` protocol and work with `@​Generable` natively! The best part is that all the APIs are already there: Bools are "noul", enums represent choices, and `@​Guide` descriptions are instructions. A Swift model implementation simply needs to handle a schema conversation, and output probabilities can be stored directly in the response metadata. developer.apple.com/document…
7
14
2
166
12,504
I clearly made some typos in the code example! 😅 The request should look like this:
1
6
878
It supports both the on-device model and Private Cloud Compute! We built it to enable effortless automations for Mac users. It's free, zero setup, no privacy compromises.
Taha Tesser@TahaTesser
Sep 20
TIL macOS 27 now comes with new fm cli 🤯 We can now use Apple's Foundation Models (on device) from CLI!
42
78
9
2,070
167,693
Richard Wei retweeted
Max Weinbach
@mweinbach
Sep 17
I've been using the on-device Apple foundation model to test out the SoC performance on the iPhone 17 Pro Max and 18 Pro Max A19 Pro Long Prompt: 2340ms TTFT, 45 tok/s Medium Prompt: 946ms TTFT, 70 tok/s Short Prompt: 638ms TTFT, 100 tok/s A20 Pro Long Prompt: 1125ms TTFT, 55 tok/s Medium Prompt: 437ms TTFT, 71 tok/s Short Prompt: 354ms TTFT, 150 tok/s
17
27
4
914
94,005
Richard Wei retweeted
Adrien Grondin
@adrgrondin
Sep 14
With iOS 27 Apple introduced its most powerful on-device model: AFM 3 Core Advanced It’s a 20 billion parameters model activating only between 1 to 4 billion parameters depending on the request Here’s the model running on iPhone 17 Pro
61
84
20
2,231
471,691
Richard Wei retweeted
Shashank Prasanna
@shshnkp
Jul 24
At our WWDC26 Recap event this week, I shared an overview of bringing intelligence into your apps on Apple platforms. 1/ Foundation Models Framework: Native Swift API for on-device, PCC & third-party LLMs (e.g. @GoogleDeepMind gemini, @claudeai, and others.) 2/ Core AI: Purpose-built framework for bringing custom models into your apps on Apple Silicon 3/ MLX: Open-source framework for model research, fine-tuning, local inference servers, and distributed computing 4/ Agentic Experiences: Multi-model workflows and context handoffs with specialized agents 5/ Evaluations: Automated tools to measure quality, uncover failures, and help you ship with confidence Watch: youtube.com/live/V2i8f_NeKDI…
1
11
72
5,626
Richard Wei retweeted
Ivan Magda@magda_ivan
Jun 12
The overview maps everything else, including the bit nobody mentions: macOS 27 ships an fm CLI, and fm serve gives you a local OpenAI-compatible endpoint backed by Apple's models. I'll update the post as I publish the rest: ivanmagda.dev/posts/wwdc26-f…

Foundation Models, Year Two: From On-Device API to General LLM Runtime | Ivan Magda

WWDC26 turned Foundation Models into Swift's general LLM client: a rebuilt on-device model, a server model with no API keys, and the first real agent primitives.

ivanmagda.dev
1
5
686
Richard Wei retweeted
Ivan Magda@magda_ivan
Jun 12
My favorite part: Dynamic Profiles. One session swaps instructions, tools, and the model mid-conversation via a SwiftUI-style body. I built these mechanisms by hand for my coding-agent series, so I mapped Apple's versions onto ours, footguns included: ivanmagda.dev/posts/foundati…

An Agent Framework Hiding Inside a Session: Dynamic Profiles in Foundation Models | Ivan Magda

Dynamic Profiles turn one LanguageModelSession into a declarative agent runtime: per-phase models, history transforms, and two orchestration patterns.

ivanmagda.dev
1
1
4
490
Richard Wei retweeted
Ivan Magda@magda_ivan
Jun 12
PrivateCloudComputeLanguageModel: a 32K-context server model with reasoning, switched on with one line. No account, no keys, no per-token bill for eligible apps. Each user spends from a daily quota instead, and that quota deserves real UI. Deep dive: ivanmagda.dev/posts/foundati…

A Server LLM With No API Keys: Private Cloud Compute in the Foundation Models Framework | Ivan Magda

Private Cloud Compute gives apps a 32K-context server model with reasoning and no API keys and makes the per-user daily quota a UI design problem.

ivanmagda.dev
1
1
6
422
Richard Wei retweeted
Ivan Magda@magda_ivan
Jun 12
Last June, Foundation Models was a Swift API to one small on-device model. After WWDC26 the same session API runs Apple's server model, Claude, Gemini, or a local Qwen. I spent the week in the betas. Three posts on what changed:
1
3
22
1,626
Richard Wei retweeted
Shashank Prasanna
@shshnkp
Jun 12
We had a blast at the Machine Learning & AI Group Lab today! ML technologies, frameworks, models, evaluations, and lots of fun with @trebolloc, @LouisDhauwe and others. 🎬 Video is up on YouTube - questions and discussions on Core AI, MLX, Foundation Models framework, Evaluations and more! WWDC26 was amazing for AI/ML. Super excited for all the incredible experiences you’ll build with these technologies! Thank you! youtube.com/live/n6TdbD7nh2k…
7
1
41
3,549
Richard Wei retweeted
Peter Friese
@peterfriese
Jun 11
You can now use Gemini via Apple's Foundation Model framework. This means: - same calls for on-device and cloud-hosted inference - you can use Grounding with Google Search / Google Maps - access to Gemini's large context window (up to 1M tokens)
2
10
1
78
7,511
Foundation Modelsめっちゃ進化してる😲iOS 27では、オンデバイスモデルにVision機能が追加されたことにより、画像に関する質問にも答えられるように。 UIImage, NSImage, CGImage, Core Image 型, CoreVideo, Pixel Buffer, ファイル URLの形式に対応。 大きな画像ほどトークンを消費する #wwdc26
1
3
1
15
2,835
Richard Wei retweeted
Shashank Prasanna
@shshnkp
Jun 10
If you missed our AI/ML Group Lab yesterday, we're doing another one on Friday June 12, 2026 9:00 AM – 10:00 AM PT. We'll discuss Core AI, Foundation Models framework, Evaluations framework and MLX. Join us! developer.apple.com/wwdc26/s…
Shashank Prasanna
@shshnkp
Jun 10
We wrapped up an amazing panel discussion on the latest in AI and Machine Learning at WWDC26. Thank you for all your questions about agents in Xcode, Core AI, Evaluations framework, Foundation Models framework, MLX. Here is the recording ICYMI. youtube.com/live/bXb18GwYQS8…

WWDC26: Coding Intelligence, Machine Learning & AI Group Lab | Apple

Join us online for a deep dive into WWDC26 with Apple engineers and...

youtube.com
8
22
2,709
Apple developers can now use @ㅤGenerable, LanguageModelSession and many familiar Swift APIs directly with Claude!
ClaudeDevs
@ClaudeDevs
Jun 10
New for Apple developers: Foundation Models support for Claude lets developers use Apple's Foundation Models framework to call Claude for multi-step reasoning, code generation, and longer context.
2
11
2,393
Richard Wei retweeted
Sahil AK
@mdsahilak
Jun 10
For WWDC26, Apple has introduced a shift in how you think about the foundation models framework. The broad "Foundation Models" term could now refer to any of these 3 things, which can be confusing. → Apple Foundation Models (AFM) - the actual on- device and server LLMs from Apple . → Foundation Models Framework - a model-agnostic layer for running LLMs on Apple devices (both local AND server, Apple AND Third-Party) . → Foundation Models Framework Utilities - An open source package that adds extra utilities for working with LLMs. Supported on apple platforms and linux. The Framework is now the main product. AFM is just one of the options you can plug in.
1
10
1
52
6,263
Richard Wei retweeted
Christopher Webb@conspirator
Jun 9
Anthropic and Google recently announced support for Apple's Foundation Models framework, making state-of-the-art Claude and Gemini models available to all Swift developers. claude.com/blog/claude-for-f… blog.google/innovation-and-a…
1
7
1
17
6,894
Wait, what? 😱 Apple Foundation Model on Private Cloud Compute is working on fm CLI! Here's a video!
12
21
5
336
39,015
Load more