# How fast is LFM2.5 1.2B on the moto g power?

> LFM2.5 1.2B writes about 13 tokens per second on the moto g power and the moto g, Galaxy A15 5G and TCL 50 XL NXTPAPER 5G in Loci, with the first word in 8.4 s. Measured on 11 phones over the last 30 days.

Canonical: https://askloci.ai/speed/dimensity-6100-plus-6300/lfm2-5-1-2b/
Last updated: 2026-10-26

About 13 tokens per second, faster than reading. The first word arrives after 8.4 seconds.

**13 tokens per second**

Faster than reading

First word in 8.4 s · a 300-word answer in about 39 s

### What 13 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 11–14 tokens per second · 11 phones

The same for the moto g, Galaxy A15 5G and TCL 50 XL NXTPAPER 5G, with the same Dimensity 6100+ / 6300 chip. · 4–8 GB

## Other models on the moto g power

- [Qwen3.5 2B](https://askloci.ai/speed/dimensity-6100-plus-6300/qwen3-5-2b/) — 8.4 tok/s · First word 4.8 s · 10 phones
- [Gemma 4 E2B](https://askloci.ai/speed/dimensity-6100-plus-6300/gemma-4-e2b/) — 4.9 tok/s · First word 5.3 s · 24 phones

- [Every model on the moto g power](https://askloci.ai/speed/dimensity-6100-plus-6300/)
- [LFM2.5 1.2B on every device](https://askloci.ai/speed/models/lfm2-5-1-2b/)

## All numbers

LFM2.5 1.2B on the moto g power, with other Android phones and models, 2026-09-26 to 2026-10-26

| Device | Model | Tokens per second | Typical range | First word | Devices | Answers |
| --- | --- | --- | --- | --- | --- | --- |
| [moto g power](https://askloci.ai/speed/dimensity-6100-plus-6300/) (Android · Dimensity 6100+ / 6300) | [LFM2.5 1.2B](https://askloci.ai/speed/models/lfm2-5-1-2b/) | 13 | 11–14 | 8.4 s | 11 | 43 |
| [moto g power](https://askloci.ai/speed/dimensity-6100-plus-6300/) (Android · Dimensity 6100+ / 6300) | [Qwen3.5 2B](https://askloci.ai/speed/models/qwen3-5-2b/) | 8.4 | 7.0–9.0 | 4.8 s | 10 | 76 |
| [moto g power](https://askloci.ai/speed/dimensity-6100-plus-6300/) (Android · Dimensity 6100+ / 6300) | [Gemma 4 E2B](https://askloci.ai/speed/models/gemma-4-e2b/) | 4.9 | 4.2–5.9 | 5.3 s | 24 | 132 |

## Run LFM2.5 1.2B 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 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.