# How fast is Apple's on-device model (iOS 27) on the iPhone 17 Pro Max?

> Apple's on-device model (iOS 27) writes about 63 tokens per second on the iPhone 17 Pro Max in Loci, with the first word in 1.3 s. Measured on 11 iPhones over the last 30 days.

Canonical: https://askloci.ai/speed/iphone-17-pro-max/apple-foundation-ios27/
Last updated: 2026-11-06

About 63 tokens per second, much faster than reading. The first word arrives after 1.3 seconds.

**63 tokens per second**

Much faster than reading

First word in 1.3 s · a 300-word answer in about 8 s

### What 63 tokens per second looks like

Sure. Start with the task you have been putting off, while your focus is fresh. Give it one uninterrupted hour, then take a short walk. Answer messages in one batch after lunch, and keep the last half hour to plan tomorrow, so the morning starts without decisions.

Typical range 59–73 tokens per second · 11 iPhones

A19 Pro · 12 GB

## Other models on the iPhone 17 Pro Max

- [Gemma 4 E2B](https://askloci.ai/speed/iphone-17-pro-max/gemma-4-e2b/) — 63 tok/s · First word 0.6 s · 27 iPhones
- [Qwen3.5 2B](https://askloci.ai/speed/iphone-17-pro-max/qwen3-5-2b/) — 51 tok/s · First word 1.2 s · 11 iPhones · 90-day sample: 2026-08-08 to 2026-11-06
- [Gemma 4 E4B](https://askloci.ai/speed/iphone-17-pro-max/gemma-4-e4b/) — 27 tok/s · First word 2.1 s · 29 iPhones

- [Every model on the iPhone 17 Pro Max](https://askloci.ai/speed/iphone-17-pro-max/)
- [Apple's on-device model (iOS 27) on every device](https://askloci.ai/speed/models/apple-foundation-ios27/)

## Run Apple's on-device model (iOS 27) on your iPhone

Loci is free, needs no account, and keeps every conversation on your device.

- [Download for iPhone](https://apps.apple.com/app/id6762100748)

30-day results and labeled 90-day samples, through November 6, 2026 · updated daily

## How these speeds are measured

- Every number comes from real chats in Loci, timed on the device that wrote the answer, with Loci's default settings.
- **Tokens per second** is how fast an answer is written once it starts. On phones, four characters of text count as one token for every model; on a Mac, Loci counts the model's own tokens. Reading pace is about 5.
- **First word** is how long an answer takes to start after you send a message. Longer conversations take longer.
- Each device counts once. The large number is the median; the typical range covers the middle half of devices.
- Results use the last 30 days when enough devices have been measured. Otherwise, labeled 90-day samples include older measurements under the same sample and app-version requirements.
- Each phone speed comes from at least 10 phones of that model. Different phone models and Android chip variants are measured separately. Open a result to see its sample size.
- On phones, answers written in Low Power Mode or Battery Saver, in the background, or with web search or other tools are left out.

[Methods, fixed editions and citations](https://askloci.ai/speed/research/)

[Check model requirements for your device](https://askloci.ai/can-my-device-run/)