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?
Show HN: Apfel – The free AI already on your Mac
161–170 of 180 posts
Re: Show HN: Apfel – The free AI already on your Mac
#162Which 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
Re: Show HN: Apfel – The free AI already on your Mac
#163I 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.
Re: Show HN: Apfel – The free AI already on your Mac
#164But by access to the private compute right?
Re: Show HN: Apfel – The free AI already on your Mac
#165wow, 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
Re: Show HN: Apfel – The free AI already on your Mac
#166Earlier quoted context omitted.
> 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. In HN circles perhaps. Average Joes don’t care.
I bet if you clearly explained the benefits and tradeoffs, and then gave them the choice, Average Joes would care.
They generally do care, but not enough to change what they do or to do without something they use, like social media.
So many people I know say “I only use Signal to talk to you”, it’s like I’m the awkward one for not using Facebook.
Re: Show HN: Apfel – The free AI already on your Mac
#167I 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.
It's only half of the solution though. If the models are trained in a closed way, they can prioritize values encoded during training even if that's not what you want (example: ask the open Chinese models about Tiananmen). It's not beyond imagining that these models would e.g. try to send your data to authorities or advertisers when their training says so, even if you run them locally. So the full solution would be mo…
All it would take is for one person to catch the model doing this and the reputation of the model and the company would be destroyed irrevocably.
Re: Show HN: Apfel – The free AI already on your Mac
#168“Already on your Mac” is a strong hook.
Curious where you see local-first AI breaking down compared to API-based workflows.
Re: Show HN: Apfel – The free AI already on your Mac
#169Saw 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. Taiwa…
What a neat LLM question! Most of my results were the same as what you posted except for the first time I asked it which resulted in this pretty interesting answer:
Taiwan is in the Taiwan Standard Time (TST) zone, which is UTC+8, while the Pacific Time (PT) zone is UTC-7.
To convert 9:30 AM Taiwan time to Pacific Time:
1. Subtract 15 hours (since 8 hours ahead is 15 hours behind).
9:30 AM - 15 hours = 6:30 AM PT.
So, 9:30 AM Taiwan time is 6:30 AM Pacific Time.
Never thought to use an llm for time zone stuff. Seems like it struggles as much as a normal person, which makes some sense given what they're trained with.
Re: Show HN: Apfel – The free AI already on your Mac
#170> 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 Appl…
I was able to confirm that it actually runs on ANE, I'm impressed.