# iPhone 18 Neural Engine Boosts AI Models

> iPhone 18's Neural Engine runs Qwen 3.8-27B model at 15-60 tps.
- Title: iPhone 18 Neural Engine Boosts AI Models | Shortify
- Summary: iPhone 18's Neural Engine runs Qwen 3.8-27B model at 15-60 tps. Apple's new iPhone 18 Neural Engine processes Qwen 3.8-27B AI model at 15-60 tps.
- Keywords: iphone 18, neural engine, qwen 3.8, ai model, apple, a20, technology, startups, iPhone, Neural, Engine, Boosts
- Source: X (formerly Twitter) — https://twitter.com/anemll/status/2111517143087067309
- Published: 2026-10-17T17:58:11+00:00
- Read time: 1 min
- Topics: iphone 18, neural engine, qwen 3.8, ai model, apple, a20, technology, startups
## iPhone 18 Neural Engine
Apple's new iPhone 18 Neural Engine processes Qwen 3.8-27B model at 15-60 tps.
## Model Performance Details
Qwen 3.8-27B runs at 15-60 tps with base model retrained on A20 Neural Engine.
## Context Processing
24K context handled with int8 K/V pairs at 70 tok/s decoding speed.
## Key takeaway

Apple's new iPhone 18 Neural Engine processes Qwen 3.8-27B AI model at 15-60 tps.