Running an AI locally means installing a language model straight onto your hard drive and chatting with it with no internet connection, no monthly subscription, and not a single one of your sentences leaving for an outside server. Ollama is the tool that makes this doable: one file to install, one command to type, and a model like Llama, Mistral or Gemma answers you at home in a matter of seconds.
The real question isn't «is this possible» (it is, even on a 2021 laptop) but «is it worth it for what I want to do». Here you'll find the actual minimum specs, a step-by-step install, which models to pick based on your RAM, and an honest comparison with the other ways to use AI. The one-line summary: local AI is excellent for privacy and for understanding how these models work, weaker on the raw quality of the answers, and useless if your goal is to produce images, videos or music.
What exactly is a local AI?
A local AI is a language model downloaded onto your computer that works out its answers using your processor and your graphics card, without going through the internet. When you use ChatGPT or Claude, your question travels to a data center, a model with several hundred billion parameters processes it, and the answer comes back. Locally, everything happens between your keyboard and your hard drive.
Two terms to know before we go further, no needless jargon:
- Parameters: this is the «size» of the model, expressed in billions (written 3B, 7B, 20B). The more parameters a model has, the more relevant it is, the more it weighs, and the more memory it needs.
- Quantization: a compression of the model so it fits in memory. By default Ollama downloads so-called Q4 versions, four times lighter than the original, with a moderate quality loss. That's what makes it possible to run a 7-billion-parameter model on an ordinary computer.
Ollama itself is not an AI. It's the program that downloads the models, launches them, manages memory, and gives you an interface to talk to them. It's free, open source, and works on macOS, Windows and Linux.
The three ways to use AI when you're starting out
Before installing anything, you should know that local AI is only one option out of three, and not the fastest one for getting concrete results. Here are all three, ordered by what works best for a beginner.
Method 1: a learning environment with the real tools included
This is Skilzy's approach. You follow a guided program (writing good prompts, creating images, automating with n8n, coding with AI) and you use professional tools directly inside the built-in «AI Lab», credits included. You install nothing, you don't stack up six €20 subscriptions just to experiment, and you don't lose three evenings getting a graphics driver to cooperate.
Why it helps when you're a beginner: you learn the method at the same time as the tool. Skilzy's 15+ AI training programs start from absolute zero, and two of them lead to a state-recognized, fundable certification (RS7439 in AI content marketing, RS6792 in AI and sales).
What this method doesn't do: it won't teach you to administer an inference server. If your goal is specifically to run a model offline on your own machine, jump to method 2.
Method 2: Ollama, the model on your own machine
Free, offline, private, no message limits. This is the method covered in the rest of this article. It asks for a decent computer, a bit of patience, and accepting one simple fact: a 7-billion-parameter model on your laptop does not reason like a cutting-edge model hosted in a data center.
Method 3: the free tiers of the big chatbots
ChatGPT, Claude and Gemini all offer free browser access, with models far more powerful than anything you'll run locally. The trade-off: daily quotas, and your conversations passing through a server. If you're torn between the three, the detailed comparison of ChatGPT, Claude and Gemini on their free plans will save you time.
These three methods combine very nicely. Plenty of people learn with a structured program, use an online chatbot day to day, and keep Ollama for sensitive documents.
What hardware you need to run Ollama
RAM is the deciding factor: Ollama's official documentation recommends at least 8 GB of RAM for a 7-billion-parameter model, 16 GB for a 13B model and 32 GB for a 33B model. Everything else is secondary.
In practice, here's what matters, in order of importance:
- RAM (or your graphics card's VRAM). The model has to fit entirely in memory, otherwise your system falls back on the disk and speed collapses. Count the size of the model file plus roughly 1 to 2 GB for everything else.
- The graphics card. A recent NVIDIA card (RTX 3060 and up) or an Apple Silicon Mac (M1 through M4, whose memory is shared between processor and graphics card) gives you smooth answers, around 20 to 60 words per second. Ollama detects your hardware on its own.
- The processor alone. It works, genuinely, but it's slow: on a laptop with no dedicated graphics card, expect 3 to 10 words per second with a small model. Fine for proofreading a text, painful for a long conversation.
- Disk space. Each model weighs between 1 and 15 GB. Plan on 20 GB free if you want to try several.
A concrete benchmark: a MacBook Air M2 with 16 GB, a PC with 16 GB of RAM and an RTX 3060, or even an 8 GB office laptop for the small models. Below 8 GB of RAM, stick to models of 1 to 3 billion parameters.
Installing Ollama and launching your first model in 10 minutes
The install comes down to three steps: download Ollama, type a command, wait for the model to download. No programming skills required.
Step 1: install Ollama. Go to the official site and grab the version for your system. On macOS and Windows, it's a regular application with a chat window. On Linux, a single line to paste into your terminal, provided on the download page.
Step 2: open a terminal. On Mac, the Terminal app. On Windows, PowerShell or Command Prompt. Type ollama --version and hit enter: if a version number shows up, you're all set.
Step 3: launch a model. Type ollama run llama3.2 then Enter. Ollama downloads roughly 2 GB the first time, then shows a prompt where you can write your question just like in any chat. To leave the conversation, type /bye.
Four commands cover day-to-day use:
- ollama list: see your installed models
- ollama pull mistral: download a model without launching it
- ollama rm mistral: delete a model and free up disk space
- ollama ps: see what's running and how much memory it's currently taking
If the terminal puts you off, Ollama also opens a small local web interface at localhost, port 11434, and free projects like Open WebUI add a layout close to ChatGPT on top of it, with conversation history and file uploads. The details are in Ollama's official documentation.
Which model to choose for your machine
Always start with the smallest model that's usable on your setup, then work your way up in size as long as the speed stays bearable. The classic beginner mistake is downloading a 20-billion-parameter model right away, watching it crawl, and concluding that local AI doesn't work.
| Model | Download size | Recommended RAM | Good for |
|---|---|---|---|
| Llama 3.2 (3B) | about 2 GB | 8 GB | First test, summaries, rewording |
| Gemma 3 (4B) | about 3 GB | 8 GB | Short texts, reading images |
| Mistral (7B) | about 4 GB | 16 GB | Writing in French, general questions |
| Qwen 3 (8B) | about 5 GB | 16 GB | Reasoning, code, multilingual |
| gpt-oss (20B) | about 14 GB | 32 GB or 16 GB of VRAM | Complex tasks, serious offline use |
Two useful notes. Models under 4 billion parameters write decent prose but make up facts easily: don't ask them for dates, figures or quotes. And none of these models has internet access: their knowledge stops at their training date, and they won't read a web page for you without extra setup.
What it's really worth: upsides and limits
Local AI wins on privacy, cost and offline availability; it loses on answer quality, speed, and anything involving images, video or sound. Given the question at hand, let's be direct.
Where Ollama is a very good choice:
- Documents you don't want to send to anyone: contracts, medical records, customer data, internal notes. Nothing leaves your machine.
- Volume: you can process 500 product descriptions without counting credits or paying per use.
- Understanding how it works: swapping models, playing with temperature, seeing how size affects quality. It's genuinely instructive, very much in line with what the guide to learning AI as a beginner covers.
- Dropped connections: trains, planes, dead zones.
Where it's the wrong solution:
- Reasoning quality. A 7B model gets things wrong far more often than a top-tier online model on a long analysis or a multi-step calculation.
- Visual and audio creation. Ollama runs text models. For images, UGC videos, voiceovers or music, you need other tools, often heavy to install and hungry for VRAM.
- Setup time. Count on one to two hours if your configuration puts up a fight (drivers, not enough memory, a poorly chosen model).
- The lack of guardrails. Nobody will tell you your prompt is bad. And that's where 80% of the result is decided, whatever the model.
One more thing to keep in mind if you want these skills to count for something: no local install goes on a résumé. A certification does. Skilzy's two certifications are registered in the Répertoire spécifique of France Compétences and can be funded through training-finance schemes, which changes things for a career-change application. If that's your situation, the article on switching careers into AI at 30, 40 or 50 walks through the possible paths.
Final word
Install Ollama, launch Llama 3.2, ask it three questions: in fifteen minutes you'll know whether your machine keeps up and whether the experience suits you. Keep local for what it does better than anyone, namely your sensitive data and high volume, and use a guided environment with real tools to learn how to produce results. The two approaches aren't in competition, they cover different needs.
