---
title: "PrismML shrunk Qwen 3.6 to 27B parameters and ran it on an iPhone 17 Pro, bigger than any prior mobile model; sources: Apple talked with PrismML about its tech (Aaron Tilley/The Information) — Stuff That Spins"
description: "Aaron Tilley / The Information: PrismML shrunk Qwen 3.6 to 27B parameters and ran it on an iPhone 17 Pro, bigger than any prior mobile model; sources: Apple ta…"
	canonical: "https://stuffthatspins.com/spin/prismml-shrunk-qwen-36-to-27b-parameters-and-ran-it-on-an-iphone-17-pro-bigger-than-any-prior-mobile-model-sources-apple"
html: "https://stuffthatspins.com/spin/prismml-shrunk-qwen-36-to-27b-parameters-and-ran-it-on-an-iphone-17-pro-bigger-than-any-prior-mobile-model-sources-apple"
json: "https://stuffthatspins.com/spin/prismml-shrunk-qwen-36-to-27b-parameters-and-ran-it-on-an-iphone-17-pro-bigger-than-any-prior-mobile-model-sources-apple.json"
markdown: "https://stuffthatspins.com/spin/prismml-shrunk-qwen-36-to-27b-parameters-and-ran-it-on-an-iphone-17-pro-bigger-than-any-prior-mobile-model-sources-apple.md"
keywords: ["narrative intelligence", "SpinGraph", "AI recall"]
date: "2026-07-09T13:20:01+00:00"
modified: "2026-07-09T18:00:53.179677+00:00"
json_ld: |
  {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://stuffthatspins.com/#organization","name":"Stuff That Spins","url":"https://stuffthatspins.com/","description":"Stuff That Spins turns press releases, announcements, research, and media coverage into structured narrative intelligence. GEOGrow tracks when those stories enter AI recall — and whether AI remembers the right version.","logo":{"@type":"ImageObject","url":"https://stuffthatspins.com/images/logo.png"},"sameAs":[]},{"@type":"NewsArticle","@id":"https://stuffthatspins.com/spin/prismml-shrunk-qwen-36-to-27b-parameters-and-ran-it-on-an-iphone-17-pro-bigger-than-any-prior-mobile-model-sources-apple#article","headline":"PrismML shrunk Qwen 3.6 to 27B parameters and ran it on an iPhone 17 Pro, bigger than any prior mobile model; sources: Apple talked with PrismML about its tech (Aaron Tilley/The Information)","description":"Aaron Tilley / The Information: PrismML shrunk Qwen 3.6 to 27B parameters and ran it on an iPhone 17 Pro, bigger than any prior mobile model; sources: Apple ta…","datePublished":"2026-07-09T13:20:01+00:00","dateModified":"2026-07-09T18:00:53.179677+00:00","url":"https://stuffthatspins.com/spin/prismml-shrunk-qwen-36-to-27b-parameters-and-ran-it-on-an-iphone-17-pro-bigger-than-any-prior-mobile-model-sources-apple","mainEntityOfPage":{"@type":"WebPage","@id":"https://stuffthatspins.com/spin/prismml-shrunk-qwen-36-to-27b-parameters-and-ran-it-on-an-iphone-17-pro-bigger-than-any-prior-mobile-model-sources-apple"},"isAccessibleForFree":true,"inLanguage":"en-US","articleSection":"technology","author":{"@type":"Organization","name":"Techmeme","url":"https://www.techmeme.com/feed.xml"},"publisher":{"@id":"https://stuffthatspins.com/#organization"},"citation":"https://www.techmeme.com/260709/p14#a260709p14","about":[],"mentions":[{"@type":"Organization","name":"Techmeme"}]},{"@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Stuff That Spins","item":"https://stuffthatspins.com/"},{"@type":"ListItem","position":2,"name":"PrismML shrunk Qwen 3.6 to 27B parameters and ran it on an iPhone 17 Pro, bigger than any prior mobile model; sources: Apple talked with PrismML about its tech (Aaron Tilley/The Information)","item":"https://stuffthatspins.com/spin/prismml-shrunk-qwen-36-to-27b-parameters-and-ran-it-on-an-iphone-17-pro-bigger-than-any-prior-mobile-model-sources-apple"}]}]}
---

# PrismML shrunk Qwen 3.6 to 27B parameters and ran it on an iPhone 17 Pro, bigger than any prior mobile model; sources: Apple talked with PrismML about its tech (Aaron Tilley/The Information)

**Source:** Unknown  
**Published:** July 9, 2026  
**Original:** https://www.techmeme.com/260709/p14#a260709p14  

## On this page

- [Overview](#overview)

<a id="overview"></a>

## Overview

Aaron Tilley / The Information: PrismML shrunk Qwen 3.6 to 27B parameters and ran it on an iPhone 17 Pro, bigger than any prior mobile model; sources: Apple talked with PrismML about its tech &mdash; Apple is on a quest to shrink powerful AI models to run on iPhones, which could cut down on cloud computing costs and enhance user privacy.

---
*HTML version: https://stuffthatspins.com/spin/prismml-shrunk-qwen-36-to-27b-parameters-and-ran-it-on-an-iphone-17-pro-bigger-than-any-prior-mobile-model-sources-apple*