Guides

Which Local AI Model Can Your Laptop Run?

Answer four quick questions about your laptop to get a local AI model that fits its memory, plus the exact Ollama commands to install it, test it and check it works.

Model sizes, commands and requirements were checked against Ollama’s model library and documentation on 17 November 2026. Speeds marked “measured” come from my own laptop; everything else is an estimate. The full walkthrough, with screenshots, is in Run local LLMs on a Windows 11 laptop with Ollama.

1

Tell me about your laptop

Which operating system do you use?

On a Mac, open the Apple menu and choose About This Mac. “Chip: Apple M…” means an Apple chip.

How much memory (RAM) does it have?
How do I check?
  • Windows: Settings, then System, then About. Look for “Installed RAM”.
  • Mac: Apple menu, then About This Mac. Look for “Memory”.
  • Linux: run free -h in a terminal and read the “total” column.

Between two sizes, for example 18 GB or 36 GB? Pick the one just below.

What will you use it for most?
What matters more to you?
2

Install Ollama

Ollama is free software that downloads AI models and runs them on your own computer. Install it once, and every model in this guide works the same way.

Windows

Download the installer from ollama.com/download/windows and run it. It installs into your user folder and does not need administrator rights. Or install it from PowerShell:

irm https://ollama.com/install.ps1 | iex

Needs Windows 10 22H2 or newer and about 4 GB of disk space for Ollama, plus room for models. NVIDIA cards need driver 551.61 or newer. AMD Radeon cards work through a ROCm v7 driver or, on many cards, Vulkan.

Mac

Download Ollama from ollama.com/download/mac, open it and drag it to Applications. Or install it from Terminal:

curl -fsSL https://ollama.com/install.sh | sh

Needs macOS 14 Sonoma or newer. Macs with an Apple chip run models on the GPU; Intel Macs run them on the processor only.

Linux

Run the official install script. It also sets Ollama up as a background service.

curl -fsSL https://ollama.com/install.sh | sh

NVIDIA cards need the NVIDIA driver (check with nvidia-smi). AMD cards need ROCm v7; see Ollama’s Linux guide.

Check that it worked

Open a new terminal window (PowerShell on Windows, Terminal on Mac) and run:

ollama --version

You should see a version number. If the terminal says ollama is not recognised, close it and open a new one. Already had Ollama? Update it: newer models such as Gemma 4 need a recent version.

3

Run your first prompt

These commands use Gemma 4 E4B, the model I tested. Answer step 1 and they switch to the model that fits your laptop.

  1. Download and start Gemma 4 E4B

    ollama run gemma4:e4b --verbose

    The first run downloads about 6.6 GB, so it can take a few minutes. --verbose makes Ollama print speed stats after each answer.

  2. Paste this test prompt at the >>> prompt

    Explain what a local AI model is in three short bullet points, and give one limitation.

    A good answer: three bullets that say it runs on your own computer and keeps your data on it, plus a real limitation, such as being slower or less capable than large cloud models.

  3. Read the speed

    When the answer finishes, Ollama prints timing stats. eval rate is how fast the model writes, in tokens per second. Anything above about 5 is faster than most people read. The first answer after loading is slower.

  4. Check where it ran

    ollama ps

    The PROCESSOR column shows whether the model is on the GPU, the CPU, or split between them. Type /bye to leave the chat.

4

Make it more useful

Work with longer documents

Below 24 GB of graphics memory, Ollama keeps about 4,000 tokens of conversation in view. For long files, raise the context length in the Ollama app’s settings. It uses more memory, so raise it in steps.

Use it inside VS Code

The free Continue extension connects VS Code to Ollama, so you can ask about your code without leaving the editor. My full write-up has the exact config.

Keep it private

Skip model tags that end in cloud: those run on Ollama’s servers, not your laptop. And keep Ollama’s port, 11434, closed to your network, because its API has no login.

Every model in this guide

Download sizes are for the default tag on Ollama’s library, checked on 17 November 2026. On a Mac, Ollama can pick a different build of the same model, so the download may be larger.

Local AI models in this guide, with download size and the memory they need
ModelOllama tagDownloadAcceptsContextGood forComfortable with
Qwen 3.5 2B
Alibaba
qwen3.5:2b2.7 GB
Mac: up to 3.1 GB
Text, images256Kchat, images16 GB RAM, a 6 GB graphics card, or an 8 GB Mac
Gemma 4 E2B
Google
gemma4:e2b4.6 GB
Mac: up to 7.5 GB
Text, images128Kchat, images16 GB RAM, an 8 GB graphics card, or a 16 GB Mac
Qwen 3.5 4B
Alibaba
qwen3.5:4b3.3 GB
Mac: up to 4 GB
Text, images256Kchat, coding, images, maths and logic16 GB RAM, a 6 GB graphics card, or a 16 GB Mac
Gemma 4 E4B
Google
gemma4:e4b6.6 GB
Mac: up to 9.5 GB
Text, images128Kchat, coding, images24 GB RAM, a 12 GB graphics card, or a 24 GB Mac
Qwen 3.5 9B
Alibaba
qwen3.5:9b6.6 GB
Mac: up to 7.6 GB
Text, images256Kchat, coding, images, maths and logic24 GB RAM, a 12 GB graphics card, or a 16 GB Mac
Gemma 4 12B
Google
gemma4:12b8 GBText, images256Kchat, coding, images, maths and logic24 GB RAM, a 12 GB graphics card, or a 16 GB Mac
gpt-oss 20B
OpenAI
gpt-oss:20b14 GBText128Kchat, coding, maths and logic32 GB RAM, a 16 GB graphics card, or a 32 GB Mac
Gemma 4 26B
Google
gemma4:26b18 GB
Mac: up to 19 GB
Text, images256Kchat, coding, images, maths and logic48 GB RAM, a 24 GB+ graphics card, or a 48 GB Mac
Qwen 3.8 27B
Alibaba
qwen3.8:27b18 GBText, images256Kchat, coding, images, maths and logic48 GB RAM, a 24 GB+ graphics card, or a 48 GB Mac

How the memory check works

Each model needs roughly its download size plus about 1.5 GB for a short conversation. The finder compares that with what your laptop can spare:

  • No separate graphics card: up to half your RAM counts as a comfortable fit, and up to three quarters if you close other apps.
  • NVIDIA or AMD graphics card: a model that fits in the card’s memory runs fastest. If it does not fit, Ollama splits it between the card and your RAM, which is slower.
  • Mac with an Apple chip: the processor and GPU share memory, and macOS keeps part of it for itself, so about 60% counts as comfortable.

Speed labels are estimates. Real speed depends on your processor, memory and drivers, so check the eval rate Ollama reports on your own machine.

Common questions

Can I run a local AI model without a graphics card?

Yes. Ollama runs models on the processor and normal RAM. On my laptop, with integrated graphics and 32 GB of RAM, Gemma 4 E4B wrote about 25.7 tokens per second, which is faster than most people read.

How much RAM do I need for a local LLM?

As a rough guide: 8 GB runs only the smallest models, such as Qwen 3.5 2B, with other apps closed. 16 GB handles 4B-class models comfortably and 9B-class models with other apps closed. 32 GB runs gpt-oss 20B. Larger models such as Qwen 3.8 27B want 48 GB of RAM or a 24 GB graphics card.

Is running AI locally free and private?

Ollama is free, and the models here are free to download under their own licences. Your prompts stay on your computer as long as you avoid model tags ending in cloud, which run on Ollama’s servers, and keep Ollama’s port closed to your network.

Gemma 4 or Qwen 3.5: which should I pick?

Both are good at laptop sizes. On my laptop, Gemma 4 E4B was faster (25.7 against 16.1 tokens per second) and answered straight away, while Qwen 3.5 thinks before it answers, which can help on harder questions. Try both on a question from your own work.

Sources