# Pixel 6 Pro

> How fast Gemma 4 E2B run on the Pixel 6 Pro, Pixel 6 and Pixel 6a (Google Tensor) in Loci: Gemma 4 E2B writes 7.6 tokens per second, first word in 6.4 s.

Canonical: https://askloci.ai/speed/google-tensor/
Last updated: 2026-10-27

Gemma 4 E2B writes 7.6 tokens per second on the Pixel 6 Pro, with the first word in 6.4 s. The Pixel 6 and Pixel 6a have the same Google Tensor chip.

### Gemma 4 E2B

**7.6 tokens per second**

Faster than reading

First word in 6.4 s · a 300-word answer in about 59 s

### What 7.6 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 5.9–11 tokens per second · 10 phones

[Gemma 4 E2B on the Pixel 6 Pro](https://askloci.ai/speed/google-tensor/gemma-4-e2b/)

- [Compare with the Pixel 7](https://askloci.ai/speed/compare/google-tensor-vs-google-tensor-g2/)
- [Compare with the iPhone 13](https://askloci.ai/speed/compare/iphone-13-vs-google-tensor/)

## Questions

### What's the fastest AI model on the Pixel 6 Pro?

Gemma 4 E2B, at 7.6 tokens per second, with the first word in 6.4 s, measured in Loci on 10 phones.

### Can the Pixel 6 Pro run Gemma 4 E2B?

Yes: Gemma 4 E2B writes 7.6 tokens per second on the Pixel 6 Pro, faster than reading, with the first word in 6.4 s.

## All numbers

Every model on the Pixel 6 Pro (Google Tensor, 6–12 GB), 2026-09-27 to 2026-10-27

| Model | Tokens per second | Typical range | First word | Devices | Answers |
| --- | --- | --- | --- | --- | --- |
| [Gemma 4 E2B](https://askloci.ai/speed/google-tensor/gemma-4-e2b/) | 7.6 | 5.9–11 | 6.4 s | 10 | 40 |

## Run Gemma 4 E2B on your phone

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

- [Get it on Android](https://play.google.com/store/apps/details?id=app.lociai.loci)

Last 30 days, through October 27, 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.
- Each phone speed comes from at least 10 phones. Fewer Macs run Loci, so each Mac speed says how many Macs it comes from.
- On phones, answers written in Low Power Mode or Battery Saver, in the background, or with web search or other tools are left out.