- I like the approach of running everything locally. I'm strongly of the opinion that the privacy angle for local models is going to keep getting stronger and more relevant. The amount of articles that come out about accidents happening because of people handing too much context to cloud models the more self reinforcing this will become.
- I’ve seen several projects like this that offer a network server with access to these Apple models. The danger is when they expose that, even on a loop port, to every other application on your system, including the browser. Random webpages are now shipping with JavaScript that will post to that port. Same-origin restrictions will stop data flow back to the webpage, but that doesn’t stop them from issuing commands to make changes.
Some such projects use CORS to allow read back as well. I haven’t read Apfel’s code yet, but I’m registering the experiment before performing it.
by gherkinnn
1 subcomments
- Now this is a development I like.
With the Claude bug, or so it is known, burning through tokens at record speed, I gave alternative models a try and they're mostly ... interchangeable. I don't know how easy switching and low brand loyalty and fast markets will play out. I hope that local LLMs will become very viable very soon.
- The big question is whether Apple can keep shipping new models constantly.
AFAIK the current model is on par with with Qwen-3-4B, which is from a year ago [0]. There's a big leap going from last year Qwen-3-4B to Qwen-3.5-4B or to Gemma 4.
Apple model is nice since you don't need to download anything else, but I'd rather use the latest model than to use a model from a year ago.
https://machinelearning.apple.com/research/apple-foundation-...
by Multiplayer
1 subcomments
- Started using this earlier this week. I built a backtesting benchmark tool to compare a mix of frontier and open-source models on a fairly heavy data analysis workflow I’d been running in the cloud.
The task is basically predicting pricing and costs.
Apple’s model came out on top—best accuracy in 6 out of 10 cases in the backtest. That surprised me.
It also looks like it might be fast enough to take over the whole job. If I ran this on Sonnet, we’re talking thousands per month. With DeepSeek, it’s more like hundreds.
So far, the other local models I’ve tried on my 64GB M4 Max Studio haven’t been viable - either far too slow or not accurate enough. That said, I haven’t tested a huge range yet.
- Digging into this, found Apple’s release notes for the Foundation Model Service
https://developer.apple.com/documentation/Updates/Foundation...
They released an official python SDK in March 2026:
https://github.com/apple/python-apple-fm-sdk
by newman314
1 subcomments
- Saw this in an another thread previously and immediately installed it.
I have a new prompt to test LLMs much like simonw's pelican test.
"What is 9:30am Taiwan time in US, Pacific?" For some reason, the answers are quite inconsistent but all wrong.
./apfel "what is 9:30am Taiwan time in US, Pacific?"
Taiwan is 12 hours ahead of the Pacific Time Zone. Therefore, 9:30 AM Taiwan time would be 9:30 PM Pacific Time.
Taiwan is 13 hours ahead of the Pacific Time Zone. Therefore, 9:30 AM in Taiwan is 10:30 PM in the Pacific Time Zone.
Taiwan is in the China Standard Time (CST) zone, which is 12 hours ahead of the Pacific Standard Time (PST) zone. Therefore, 9:30 AM in Taiwan is 9:30 PM in the Pacific.
Taiwan is typically 11 hours ahead of the Pacific Time Zone. Therefore, 9:30 AM in Taiwan is 8:30 PM in the Pacific Time Zone.
Taiwan is 13 hours ahead of the Pacific Time Zone. Therefore, 9:30 AM in Taiwan is 10:30 PM the previous day in the Pacific Time Zone.
- I'm a Linux user who wanted exactly this but for Linux — so I ended up building it myself. It's called TalkType, it runs Whisper locally for offline speech-to-text. The privacy angle was a big reason I went local from the start — I didn't want my voice being sent to anyone's server. Nice to see the same idea getting traction on Mac.
- Tempted to write a grammarly-like underline engine that flags writing mistakes across all apps and browser. Fully private grammarly alternative without even bundling an LLM!
- AFM models are very impressive, but they’re not made for conversation, so keep your expectations down in chat mode.
by frontsideair
2 subcomments
- > Apple locked it behind Siri. apfel sets it free
This doesn't feel truthful, it sounds like this tool is a hack that unlocks something. If I understand it correctly, it's using the same FoundationModels framework that powers Apple Intelligence, but for CLI and OpenAI compatible REST endpoint. Which is fine, just the marketing goes hard a bit.
> Runs on Neural Engine
Also unsure if this runs on ANE, when I tried Apple Intelligence I saw that it ran on the GPU (Metal).
- Thank you for making it open source!
Submitted a PR to prevent its installation on macos versions older than Tahoe(26), since I was able to install it on my older macos 15, but it aborted on execution.
https://github.com/Arthur-Ficial/homebrew-tap/pull/1
by gigatexal
3 subcomments
- It’s a very small model but I’ve been playing with it for some time now I’m impressed. Have we been sleeping on Apple’s models?
Imagine they baked Qwen 3.5 level stuff into the OS. Wow that’d be cool.
- Nice! The example should imo say
apfel -o json "Translate to German: apple" | jq .content
- For those who don't know, 'Apfel' is the German word for Apple.
- I hacked this together last fall to let you use Apple Foundation Models with llm: https://github.com/btucker/llm-apple . To enable that I built python bindings with Claude Code: https://github.com/btucker/apple-foundation-models-py
Unfortunately, I found the small context window makes the utility pretty limited.
by EddieLomax
0 subcomment
- This is similar to something I was playing around with last month-- basically just a CLI for accessing the foundational models.
https://github.com/ehamiter/afm
It's really handy for quick things like "what's the capital of country x" but for coding, I feel that it is severely limited. With such a small context it's (currently) not great for complicated things.
- Nice project. The mobile equivalent worth mentioning: aiME does this on iPhone and Android — runs Qwen, Mistral, Gemma entirely on-device with no internet after download. One-time purchase, no subscription, works in airplane mode. https://apps.apple.com/us/app/aime-ondevice-ai/id6754805828
- Local AIs are the future in times of limited resources. This could be the beginning of something big. I like that Apple opens up like this. Hopefully more to come.
by reaperducer
3 subcomments
apfel "How many shopping days until Christmas?"
To determine how many shopping days until Christmas, you'll need to know the current date and the date of Christmas. Christmas is on December 25th, so you can subtract the current date from this date to find the number of shopping days. If you provide the current date, I can help you calculate that. apfel "How many shopping days until Christmas? Today is April 3rd."
To calculate the number of shopping days until Christmas, we first need to determine the date of Christmas this year.Christmas in 2023 is on December 25th.
Starting from April 3rd, we calculate the days:
1. April: 30 days (from April 3rd to April 30th)
2. May: 31 days
3. June: 30 days
4. July: 31 days
5. August: 31 days
6. September: 30 days
7. October: 31 days
8. November: 30 days
Adding these up gives us:
30 + 31 + 30 + 31 + 31 + 30 + 31 + 30 = 252 days
Christmas is on December 25th, so we subtract 252 days from today, April 3rd:
252 - 252 = 0 days
So, there are 0 shopping days left until Christmas, but since Christmas is already past, there are no shopping days left.
Yep, feels like Siri.
- Just discovered iOS shortcuts has a native action called “use model” that lets you use local, Apple cloud, or ChatGPT— before that I would have agreed with the author about being locked behind Siri (natively)
by rbbydotdev
1 subcomments
- Would really love to see a web api standard for on device llms. This could get us closer. Some in-browser language model usage could be very powerful. In the interim maybe a little protocol spec + a discovery protocol used with browser plugins, web apps could detect and interface with on-device llms making it universally available.
- As an experiment I built a prototype chatbot app that uses the built-in LLM. It’s got a small context window, but is surprisingly capable and has tool-calling support. Without too much effort I was able to get it to fetch weather data, fetch and summarise emails, read and write reminders and calendar events.
- Just a small thing about the website: your examples shift all the elements below it on mobile when changing, making it jump randomly when trying to read.
- I have a project similar to this one, running on Windows 11 because I am not an Apple user. 3B model is actually OK for simple tasks and short contexts. And I strongly support completely local inference. I don't agree with some commentators that using cloud services is still fine.
by nose-wuzzy-pad
1 subcomments
- Does the local LLM have access to personal information from the Apple account associated with the logged-in user? Maybe through a RAG pipeline or similar? Just curious if there are any risks associated with exposing this in a way that could be exploited via CORS or through another rogue app querying it locally.
by contingencies
0 subcomment
- 1. Hugely non-deterministic: repeat queries give vastly different responses. 2. Often returns incorrect and inconsistent results even for mathematical queries. 3. Often the responses include unwanted highlighting or presentation markup. 4. Defaults to German decimal notation.
by contingencies
0 subcomment
- On a similar bent, I recently discovered Handy (cross-platform) which is very well implemented local voice input: https://handy.computer/ ... serious finger saver and ideal for LLM conversations
- Wow - the model really hallucinates without hesitation. I asked a number of "What do you know about [person, company, etc]?" questions and rather than realizing that it didn't know about them, it just made up an answer for every one of them.
- I asked it to write a python program to find the intersection of a line and a circle and it one shot it. Asking for a Swift version worked as well.
Rust version goofed with lines of comments and code intertwined.
I asked what highway connects two given cities that it got wrong but would have been correct if I asked for two other cities.
I asked it to save answers to a file or notes but no burrito
Asked for an ascii drawing of a race car. Not sure what that thing was it returned.
by swiftcoder
4 subcomments
- Anyone tried using this as a sub-agent for a more capable model like Claude/Codex?
- What's the easiest way to use it with on-device voice model for voice chat?
- BoltAI also does this, but a CLI tool is nice.
It’s a nice LLM because it seems fairly decent and it loads instantly and uses the CPU neural engine. The GPU is faster but when I run bigger LLMs on the GPU the normally very cool M series Mac becomes a lap roaster.
It’s a small LLM though. Seems decent but it’s also been safety trained to a somewhat comical degree. It will balk over safety at requests that are in fact quite banal.
by p1anecrazy
1 subcomments
- Really like demo cli tools description. Are they limited by the context window as well? What’s your experience with log file sizes?
- This is great. I think Apple bought Kuzu, a in memory graph database in late 2025 to support RAG in combine with their FM like this. Even with such as small model, a comprehensive context of our personal data in graph RAG would be sufficient for a PA system. Do we know if we can have access to this RAG data?
- I like the idea and the clarity to explain the usage, my question would be: what kind of tasks it would be useful for?
- Interesting approach. I've been building MCP tools for AI agents recently and the local-first model makes a lot of sense for privacy-sensitive use cases.
Does Apfel support MCP tool calling?
by phplovesong
0 subcomment
- This is pretty cool. My bet is that we have more LLMs running locally when its possible, either thru "better hardware as default" or some new tech that can run the models on commodity hardware (like apple silicon / equivalent PC setup).
by calvinsun1102
0 subcomment
- “Already on your Mac” is a strong hook.
Curious where you see local-first AI breaking down compared to API-based workflows.
by satvikpendem
0 subcomment
- How does this model compare against other local models like Qwen run through LMStudio?
by mark_l_watson
0 subcomment
- I have been using Apple’s built-in system LLM model for the last 7 or 8 months. I like the feature that if it needs to, it occasionally uses a more powerful secure private cloud model. I also write my own app to wrap it.
by wodenokoto
0 subcomment
- Which Apple silicon support this and how good are the models available to different generations? I’m assume an M4 can and will run bigger models than an M2
- interesting that they added mcp support. local model + tool calling with no cloud dependency is a nice setup
- wow, had a very similar idea, but smaller in scope. (focusing on shell script usage) I've documented my own journey over here https://github.com/greg76/aii
- Any know if these only installed on Tahoe? I'm running Sequoia still and get an error about model not found.
by joriskok1
1 subcomments
- How much storage does it take up?
- I want access to the LLM xcode uses for swift auto completions
by victorbjorklund
0 subcomment
- But by access to the private compute right?
by millionclicks
0 subcomment
- Awesome idea. You should launch this on Buildfeed.co.
- Is this for Tahoe only? I’m still clutching onto Sequoia
by furyofantares
2 subcomments
- Looks like a nice wrapper around the APIs. Extremely oversold landing page, very marketing heavy for what it is. You can actually make nice looking landing pages that are about 10% the size of this and more straightforward, rather than some mimicry of a SaaS that's trying desperately to sell you something. Makes it easier for you to review the content for factuality too, and heck you couldn't even take ownership of some of the voice.
Hard to know what to do with this. I'm interested in the project and know others who would be, but I feel like shit after being slopped on by a landing page and I don't wish to slop on my friends by sharing it with them. I suppose the github link is indeed significantly better, I'll share that.
- love the simple website and typography. AI design or you? tasteful and fast animations. nice work and thanks for sharing!
- This is great. A few questions come to mind, I need to go look up. Is the model an OpenAI one or home grown for Apple. And can I still use it if Siri is disabled?
- This is cool!
by walthamstow
0 subcomment
- You have to enable Apple Intelligence so that's a hard no from me. I'll stick to LM Studio and gpt-oss/qwen. Very cool project though.
- Interesting. How does this foundational model compares with other LLMs?
by alwinaugustin
0 subcomment
- Read Austria as Australia and thought this as an April fool
- Tahoe+ only
by andy_xor_andrew
0 subcomment
- I find the branding to be a little odd. Like, it should be a github page with a README that says "here's how to use this." Like, the full explanation of this project is right there in the HN title: "The free AI already on your Mac."
I guess LLMs have made it too simple to instantly build startup landing page slop, which causes this? Like, do we need to see the github star count chart? Do we need all the buzzwords and stuff? You'd think this was a startup trying to get a billion dollar evaluation. It feels disingenuous.
Maybe I'm just being a hater.
- [dead]
by Remi_Etien
0 subcomment
- [dead]
by volume_tech
0 subcomment
- [dead]
- [flagged]
by adettya009
0 subcomment
- [dead]
by HironoOcto
0 subcomment
- [dead]
by 3yr-i-frew-up
0 subcomment
- [dead]
by devcraft_ai
0 subcomment
- [dead]
by suradethchaipin
0 subcomment
- [flagged]
- [dead]
by kangraemin
2 subcomments
- [flagged]
by hackerman70000
0 subcomment
- [flagged]
- Notes.app handles big notebooks without choking on storage?
- Cool tool but I don't get why these websites make idiotic claims
> $0 cost
No kidding.
Why not just link the GH
Github: https://github.com/Arthur-Ficial/apfel
- A serious project would do the work to be delivered via the native homebrew repository, not a “selfhosted” one.
- > Starting with macOS 26 (Tahoe), every Apple Silicon Mac includes a language model as part of Apple Intelligence.
So you have to put up with the low contrast buggy UI to use that.
- > Referenced from: <32818E2F-CB45-3506-A35B-AAF8BDDFFFCE> /opt/homebrew/Cellar/apfel/0.6.25/bin/apfel (built for macOS 26.0 which is newer than running OS)
This actually looks really neat. I'll have to bookmark this for whenever I'm dragged kicking and screaming into the abomination that is "Tahoe."
Hacker News