Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
lemonish97
13 days ago
|
parent
|
context
|
favorite
| on:
Gemma 3 270M: Compact model for hyper-efficient AI
Never thought I'd run an LLM released in 2025, on my phone, in full BF16. With ~80tps on an iPhone 16 pro btw.
elAhmo
13 days ago
[–]
How do you actually run this on an iPhone?
reply
CharlesW
13 days ago
|
parent
|
next
[–]
With something like PocketPal AI (
https://github.com/a-ghorbani/pocketpal-ai
). I'd love hear HN'ers opinions on the "best" LM Studio-like option for iOS devices.
reply
sogen
13 days ago
|
root
|
parent
|
next
[–]
For iOS, OpenCat. Has iCloud sync, and one universal app for MacOS and iOS devices.
reply
lemonish97
13 days ago
|
parent
|
prev
[–]
I use PocketPal. Can run any gguf model off hf.
reply
rshemet
13 days ago
|
root
|
parent
[–]
you can also run it on Cactus - either in Cactus Chat from the App/Play Store or by using the Cactus framework to integrate it into your own app
reply
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: