Can an Intel Core Ultra 5 laptop run AI? Measured: 14–18 tokens a second
Yes. On a laptop with no graphics card (Intel Core Ultra 5 125U) and 16 GB of RAM, Gemma 4 E2B wrote 14–18 tokens a second. You read about 5, so answers come out faster than you can read them.
What that means in practice
| Task | Time on this PC |
|---|---|
| Write a normal answer (400 tokens, about 300 words) | 22–29 s |
| Make a picture (512×512, built-in graphics) | 2:02–2:38 min |
| Make a picture (512×512, processor alone) | 11:27–13:32 min |
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), 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 |
|---|---|---|---|
| Gemma 4 E2B | processor only | 14–18 tokens a second writing | 28 September 2026 1 |
| Gemma 4 E4B | processor only | 8–10 tokens a second writing | 28 September 2026 1 |
| Picture (512×512) | built-in Intel graphics | 2:02–2:38 min | 27 September 2026 2 |
| Picture (512×512) | processor only | 11:27–13:32 min | 14 October 2026 2 |
How each number was measured:
- llama.cpp's own speed test (llama-bench), the engine GreenCube runs on, with the same AI files: 128 tokens written, a 512-token text read.
- 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
No graphics card? It still works
With no graphics card, the AI runs on the processor. It is slower than on a gaming PC, but the smaller Gemma 4 E2B still writes 14–18 tokens a second, enough to study, summarise and write with. The bigger Gemma 4 E4B works too, at 8–10: smarter, but you will feel the wait on long answers.
Pictures
Yes. One picture (512×512) took 2:02–2:38 min on the built-in Intel graphics, and 11:27–13:32 min on the processor alone. 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 2 PCs we measured with Gemma 4 E2B, this one is number 1 for writing speed. The Intel Iris Xe laptop writes 5–7, so this one is about 2.5 times as fast.
The test PC
A real tester's own PC, used the way they normally use it, not a lab machine:
- Laptop
- Graphics: built-in Intel graphics only
- Graphics memory (VRAM): none (no separate graphics card)
- RAM: 16 GB
- Processor: Intel Core Ultra 5 125U, 14 threads
Check your own PC
Not sure what your PC has? It takes 30 seconds:
- Press Ctrl + Shift + Esc to open Task Manager.
- Go to Performance.
- Click Memory: the number at the top right is your RAM.
- 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. 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: 65–71 tokens a second (Gemma 4 E4B)
- RX 5700 XT: 63–72 tokens a second (Gemma 4 E4B)
- RTX 5060: 56 tokens a second (Gemma 4 E4B)
- RTX 3060: 53–55 tokens a second (Gemma 4 E4B)
- RX 6600: 42–44 tokens a second (Gemma 4 E4B)
- GTX 1660 Super: 37–38 tokens a second (Gemma 4 E4B)
- GTX 1650: about 20 tokens a second (Gemma 4 E4B)
- RX 580: 10–11 tokens a second (Gemma 4 E4B)
- Intel Iris Xe laptop: 5–7 tokens a second (Gemma 4 E2B)
Can my PC run AI? All 10 PCs in one table, and what your PC will feel like.
Questions
Can an Intel Core Ultra 5 laptop run AI locally?
Yes. On a laptop with no graphics card (Intel Core Ultra 5 125U) and 16 GB of RAM, Gemma 4 E2B wrote 14–18 tokens a second. You read about 5, so answers come out faster than you can read them.
Can an Intel Core Ultra 5 laptop make AI pictures?
Yes. One picture (512×512) took 2:02–2:38 min on the built-in Intel graphics, and 11:27–13:32 min on the processor alone.
Your own AI, on your own PC
GreenCube runs on your computer: no usage limits, no subscription, works without internet. €9.99, paid once.
Get GreenCube