# How fast is Qwen3.5 2B on the M3 Mac with 8 GB?

> Qwen3.5 2B writes about 23 tokens per second on the M3 Mac with 8 GB in Loci, with the first word in 13.7 s. Measured on 2 Macs over the last 30 days.

Canonical: https://askloci.ai/speed/mac-m3-8gb/qwen3-5-2b/
Last updated: 2026-10-26

About 23 tokens per second, much faster than reading. The first word arrives after 13.7 seconds.

**23 tokens per second**

Much faster than reading

First word in 13.7 s · a 300-word answer in about 31 s

### What 23 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

M3 · 8 GB

## Qwen3.5 2B on other Macs

- [M2 Mac with 8 GB](https://askloci.ai/speed/mac-m2-8gb/qwen3-5-2b/) — 44 tok/s · First word 9.6 s · 2 Macs
- [M3 Mac with 8 GB](https://askloci.ai/speed/mac-m3-8gb/qwen3-5-2b/) — 23 tok/s · First word 13.7 s · 2 Macs

- [Every model on the M3 Mac with 8 GB](https://askloci.ai/speed/mac-m3-8gb/)
- [Qwen3.5 2B on every device](https://askloci.ai/speed/models/qwen3-5-2b/)

## All numbers

Qwen3.5 2B on the M3 Mac with 8 GB, with other Macs and models, 2026-09-26 to 2026-10-26

| Device | Model | Tokens per second | Typical range | First word | Devices | Answers |
| --- | --- | --- | --- | --- | --- | --- |
| [M3 Mac with 8 GB](https://askloci.ai/speed/mac-m3-8gb/) (Mac · M3) | [Qwen3.5 2B](https://askloci.ai/speed/models/qwen3-5-2b/) | 23 | — | 13.7 s | 2 | — |
| [M2 Mac with 8 GB](https://askloci.ai/speed/mac-m2-8gb/) (Mac · M2) | [Qwen3.5 2B](https://askloci.ai/speed/models/qwen3-5-2b/) | 44 | — | 9.6 s | 2 | — |

## Run Qwen3.5 2B 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 26, 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.