# Can an RTX 3060 run AI? Measured: 53–55 tokens a second

> Real test: Cube 4B (Gemma 4 E4B) wrote 53–55 tokens a second on a desktop with an NVIDIA RTX 3060 (12 GB) and 32 GB of RAM. What it means for chat, study and pictures.

Canonical: https://blog.greencube.app/blog/ai-on-rtx-3060  
Published: 2026-10-06  
Author: Hector Gras

**Yes.** On a desktop with an NVIDIA RTX 3060 (12 GB) and 32 GB of RAM, Cube 4B (Gemma 4 E4B) wrote 53–55 tokens a second. You read about 5, so answers come out faster than you can read them.

- **53–55** tokens a second with Cube 4B (Gemma 4 E4B)
- **7.5×** faster on the card than on the processor
- **28 s** to make a picture

## What that means in practice

| Task | Time on this PC |
| --- | --- |
| Write a normal answer (400 tokens, about 300 words) | **7–8 s** |
| Read a long document you give it (5,000 tokens, about 7 pages) | **4–5 s** |
| Make a picture (512×512) | **28 s** |

Worked out from the speeds measured on this PC: time is length divided by speed, and a real answer also spends a moment getting started. For scale, most people read about 4 words a second ([Brysbaert, 2019](https://doi.org/10.1016/j.jml.2019.104047)), so a 400-token answer takes you over a minute just to read.

## What we measured

**Writing** is how fast the AI types its answer, in tokens a second; a token is about three quarters of an English word. **Reading** is how fast it takes in what you give it: your question, a pasted text or a PDF. Reading is always much faster than writing, because the AI can read many tokens at once but has to write them one by one.

| What | Ran on | Result | Measured |
| --- | --- | --- | --- |
| Cube 4B (Gemma 4 E4B) | graphics card | **52.6–55.3** tokens a second writing · 1,044–1,362 reading | 6 October 2026 [1] |
| Cube 4B (Gemma 4 E4B) | graphics card | **49.6–55.4** tokens a second writing | 6 October 2026 [2] |
| Cube 4B (Gemma 4 E4B) | processor only | **6.7–7.3** tokens a second writing | 6 October 2026 [2] |
| Picture (512×512) | graphics card | **28 s** | 3 October 2026 [3] |

How each number was measured: [More on how we measure](https://blog.greencube.app/blog/how-we-measure-ai-speed)

1. Real chats in GreenCube 0.1.42–0.1.43: the speed of every answer of 100 tokens or more, read from the app's log. The range leaves out the slowest and the fastest tenth.
2. GreenCube 0.1.42–0.1.43's own speed test, which it runs at startup to choose between the graphics card and the processor: a short answer written once on each.
3. GreenCube's picture engine (Z-Image Turbo), 512×512 pixels, 8 steps, timed from the click to the finished picture.

Where we have several runs we show the range: speeds move a little between runs on the same PC.

## What it means

### The graphics card does the work

Same PC, same AI (Cube 4B (Gemma 4 E4B)): 6.7–7.3 tokens a second on the processor alone, 49.6–55.4 on the graphics card, about **7.5 times faster**. A graphics card is built to do thousands of small sums at once for games, and running an AI is mostly that same kind of maths. GreenCube times both when it starts and uses the faster one.

### The whole AI fits on the card

Cube 4B (Gemma 4 E4B) is a 4.2 GB file and the card has 12 GB of its own memory (VRAM). All of it fits, with room left for the conversation, so the card never waits for the slower memory in the rest of the PC. That is the biggest reason it runs this fast.

### The bigger Cube 12B (Gemma 4 12B)

It should. Cube 12B (Gemma 4 12B) is a 6.4 GB file and this card has 12 GB, which leaves room for a long conversation too. We haven't measured it on this card yet.

### Pictures

Yes. One picture (512×512) took 28 s on the graphics card. A picture uses its own AI of about 6 GB and far more maths than a chat answer, so the graphics matter even more here.

## How it compares

Of the 8 PCs we measured with Cube 4B (Gemma 4 E4B), this one is **number 4** for writing speed. The [RTX 5060](https://blog.greencube.app/blog/ai-on-rtx-5060) writes 56 (startup test), about 5% faster. The [RX 6600](https://blog.greencube.app/blog/ai-on-rx-6600) writes 42–44, so this one is about 25% faster.

## The test PC

A real tester's own PC, used the way they normally use it, not a lab machine:

- Desktop
- **Graphics:** NVIDIA RTX 3060
- **Graphics memory (VRAM):** 12 GB
- **RAM:** 32 GB
- **Processor:** 12 threads

## Check your own PC

Not sure what your PC has? It takes 30 seconds:

1. Press **Ctrl + Shift + Esc** to open Task Manager.
2. Go to **Performance**.
3. Click **Memory**: the number at the top right is your RAM.
4. Click **GPU**: the name at the top right is your card, and **Dedicated GPU memory** is your VRAM. Only see Intel or AMD graphics with no dedicated memory? Then you have no separate card.

Then find the closest card in [the full table](https://blog.greencube.app/blog/can-my-pc-run-ai). The same card with more VRAM can fit a bigger AI; a newer card of the same size is usually faster.

## Other PCs we measured

- [RTX 2080 Ti](https://blog.greencube.app/blog/ai-on-rtx-2080-ti): 65–71 tokens a second (Cube 4B (Gemma 4 E4B))
- [RX 5700 XT](https://blog.greencube.app/blog/ai-on-rx-5700-xt): 63–72 tokens a second (Cube 4B (Gemma 4 E4B))
- [RTX 5060](https://blog.greencube.app/blog/ai-on-rtx-5060): 56 tokens a second (Cube 4B (Gemma 4 E4B))
- [RX 6600](https://blog.greencube.app/blog/ai-on-rx-6600): 42–44 tokens a second (Cube 4B (Gemma 4 E4B))
- [GTX 1660 Super](https://blog.greencube.app/blog/ai-on-gtx-1660-super): 37–38 tokens a second (Cube 4B (Gemma 4 E4B))
- [GTX 1650](https://blog.greencube.app/blog/ai-on-gtx-1650): about 20 tokens a second (Cube 4B (Gemma 4 E4B))
- [Intel Core Ultra 5 laptop](https://blog.greencube.app/blog/ai-on-intel-core-ultra-5-laptop): 14–18 tokens a second (Cube 2B (Gemma 4 E2B))
- [RX 580](https://blog.greencube.app/blog/ai-on-rx-580): 10–11 tokens a second (Cube 4B (Gemma 4 E4B))
- [Intel Iris Xe laptop](https://blog.greencube.app/blog/ai-on-intel-iris-xe-laptop): 5–7 tokens a second (Cube 2B (Gemma 4 E2B))

[Can my PC run AI?](https://blog.greencube.app/blog/can-my-pc-run-ai) All 10 PCs in one table, and what your PC will feel like.

## FAQ

### Can an RTX 3060 run AI locally?

Yes. On a desktop with an NVIDIA RTX 3060 (12 GB) and 32 GB of RAM, Cube 4B (Gemma 4 E4B) wrote 53–55 tokens a second. You read about 5, so answers come out faster than you can read them.

### Can an RTX 3060 make AI pictures?

Yes. One picture (512×512) took 28 s on the graphics card.

### Is AI faster on the RTX 3060 or on the processor?

On the card, by far: 49.6–55.4 tokens a second against 6.7–7.3 on the processor, about 7.5 times faster.

### Can an RTX 3060 run Gemma 4 12B?

It should. Cube 12B (Gemma 4 12B) is a 6.4 GB file and this card has 12 GB, which leaves room for a long conversation too. We haven't measured it on this card yet.
