# M5 Mac with 16 GB

> How fast Gemma 4 E4B run on the M5 Mac with 16 GB (M5) in Loci: Gemma 4 E4B writes 33 tokens per second, first word in 0.5 s.

Canonical: https://askloci.ai/speed/mac-m5-16gb/
Last updated: 2026-10-27

Gemma 4 E4B writes 33 tokens per second on the M5 Mac with 16 GB, with the first word in 0.5 s.

### Gemma 4 E4B

**33 tokens per second**

Much faster than reading

First word in 0.5 s · a 300-word answer in about 13 s

### What 33 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.

Measured on 2 Macs

[Gemma 4 E4B on the M5 Mac with 16 GB](https://askloci.ai/speed/mac-m5-16gb/gemma-4-e4b/)

## Questions

### What's the fastest AI model on the M5 Mac with 16 GB?

Gemma 4 E4B, at 33 tokens per second, with the first word in 0.5 s, measured in Loci on 2 Macs.

### Can the M5 Mac with 16 GB run Gemma 4 E4B?

Yes: Gemma 4 E4B writes 33 tokens per second on the M5 Mac with 16 GB, much faster than reading, with the first word in 0.5 s.

## All numbers

Every model on the M5 Mac with 16 GB (M5, 16 GB), 2026-09-27 to 2026-10-27

| Model | Tokens per second | Typical range | First word | Devices | Answers |
| --- | --- | --- | --- | --- | --- |
| [Gemma 4 E4B](https://askloci.ai/speed/mac-m5-16gb/gemma-4-e4b/) | 33 | — | 0.5 s | 2 | — |

## Run Gemma 4 E4B on your Mac

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

- [Download for Mac](https://askloci.ai/private-ai-mac/)

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.