<!-- mobian-agent-page publisher="dailydev" canonical="https://daily.dev/posts/apple-eyes-prismml-s-on-device-ai-for-the-iphone-lsvdpozuw" -->

---
title: Apple eyes PrismML’s on-device AI for the iPhone | daily.dev
description: Apple is in early talks with PrismML, a Caltech spinout backed by Khosla Ventures, about its AI model compression technology. PrismML released Bonsai 27B, a...
canonical: https://daily.dev/posts/apple-eyes-prismml-s-on-device-ai-for-the-iphone-lsvdpozuw
twitter:card: summary_large_image
twitter:site: @dailydotdev
og:type: website
og:site_name: daily.dev
og:title: Apple eyes PrismML’s on-device AI for the iPhone | daily.dev
og:description: Apple is in early talks with PrismML, a Caltech spinout backed by Khosla Ventures, about its AI model compression technology. PrismML released Bonsai 27B, a...
og:url: https://daily.dev/posts/apple-eyes-prismml-s-on-device-ai-for-the-iphone-lsvdpozuw
og:image: https://api.daily.dev/og/posts/LsVDPOzuw.png
og:image:alt: Apple eyes PrismML’s on-device AI for the iPhone
og:image:width: 1200
og:image:height: 630
og:locale: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Apple eyes PrismML’s on-device AI for the iPhone

**[The Next Web](https://daily.dev/sources/tnw)** · 3 min read · 0 upvotes · 0 comments

## Summary

Apple is in early talks with PrismML, a Caltech spinout backed by Khosla Ventures, about its AI model compression technology. PrismML released Bonsai 27B, a compressed version of Alibaba's Qwen model shrunk from 54GB to 3.9GB using 1-bit and ternary quantization. The 1-bit build is designed to fit within iPhone 17 Pro's memory budget, running a 27B-parameter model on-device. The compression achieves 10-15x memory reduction, 6-8x speed improvement, and 3-6x energy savings, at a cost of roughly 5-10% performance degradation. Apple's interest is driven by its Siri overhaul in iOS 27, privacy goals, reduced cloud costs, and hardware memory constraints. Analysts note that real-world performance across millions of devices remains unproven, and that edge AI shifts compute from data centers to phones rather than eliminating it.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://thenextweb.com/news/apple-prismml-on-device-ai-compression-iphone>

## Similar posts on daily.dev

- [PrismML — Introducing Ternary Bonsai: Top Intelligence at 1.58 Bits](https://daily.dev/posts/prismml-introducing-ternary-bonsai-top-intelligence-at-1-58-bits-klkxnwryn) · Hacker News · 1 upvotes · 0 comments
- [I ran the tiny Bonsai model on my tiny GPU. Here’s how it performed](https://daily.dev/posts/i-ran-the-tiny-bonsai-model-on-my-tiny-gpu-here-s-how-it-performed-dsp1h8gia) · InfoWorld · 0 upvotes · 0 comments

---

Tags: [#apple](https://daily.dev/tags/apple), [#local-ai](https://daily.dev/tags/local-ai), [#edge-ai](https://daily.dev/tags/edge-ai)

[View this post on daily.dev](https://daily.dev/posts/apple-eyes-prismml-s-on-device-ai-for-the-iphone-lsvdpozuw)

```json
{"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]}
{"@context":"https://schema.org","@type":"TechArticle","headline":"Apple eyes PrismML’s on-device AI for the iPhone","url":"https://daily.dev/posts/apple-eyes-prismml-s-on-device-ai-for-the-iphone-lsvdpozuw","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/apple-eyes-prismml-s-on-device-ai-for-the-iphone-lsvdpozuw"},"datePublished":"2026-07-15T14:19:13.548Z","dateModified":"2026-07-15T14:41:11.873Z","description":"Apple is in early talks with PrismML, a Caltech spinout backed by Khosla Ventures, about its AI model compression technology. PrismML released Bonsai 27B, a...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/8eecbbb8270f2c3caebef386bb698332?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/8eecbbb8270f2c3caebef386bb698332?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"The Next Web","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"The Next Web","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/tnw","url":"https://daily.dev/sources/tnw"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/apple-eyes-prismml-s-on-device-ai-for-the-iphone-lsvdpozuw","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"apple,local-ai,edge-ai","timeRequired":"PT3M"}
{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"The Next Web","item":"https://daily.dev/sources/tnw"},{"@type":"ListItem","position":3,"name":"Apple eyes PrismML’s on-device AI for the iPhone"}]}
```

