NederlandsLocal AI
Local AI is an AI model that runs on your own computer or phone instead of on a company's servers. Your data stays with you, and it often works without internet too.
With local AI, the AI model runs on your own device: a laptop, a mini computer or a phone. Your questions then do not have to go to a company's servers. It is like cooking at home instead of having a meal delivered: you need the kitchen yourself, but nobody else is looking over your shoulder.
How does it work?
An AI model is basically just a large file of numbers. If the model is open, anyone can download it and run it on their own hardware. The problem is size. The strongest models take up hundreds of gigabytes and normally only run in a data centre.
That is why models are often shrunk. A common way is quantisation: the numbers in the model are rounded off, so that the file becomes much smaller. This costs some accuracy. In addition, smaller models are made that are intended for a laptop or phone from the start.
Why it matters
Local AI gives control. Researchers, small companies and hospitals can use a model without sending their data elsewhere. And it also works when there is no internet. The company Gradium, for instance, released Phonon openly: small models that read text aloud in a natural voice, entirely on a phone, laptop or in the browser (link).
Ever larger models are coming within reach. DeepSeek's open model is well over 500 gigabytes, but the company Unsloth made a heavily shrunk version of it that runs on a powerful laptop or mini computer with 128 gigabytes of memory (link). The answer does come more slowly than from a chatbot in a data centre. There is something for the laptop when it comes to programming, too: the AI company Recursive released Flint, a free model that helps with coding. According to the company, its own research AI did a large part of the development work (link).
Articles about Local AI
-
Small open AI model reads text aloud on your phone, without internet
The AI company Gradium has released Phonon as open models: small text-to-speech models that read text aloud with a natural voice, entirely on a phone, a laptop or in the browser. On a public Hugging Face leaderboard, Phonon is among the most intelligible text-to-speech models.
-
Unsloth shrinks a large open AI model from Alibaba and, by its own tests, makes it more accurate than other versions
Unsloth has released new, smaller versions of Qwen3.8-Flash-Next, a large open AI model from Alibaba. By its own tests, they score 15 per cent higher on average than other shrunken versions. This lets more people run the model on their own computers.
-
Developer builds a complete processor inside the weights of an AI language model
Developer Divyansh Agrawal built a complete processor inside the weights of the language model Qwen 3.5. In his tests, the model now calculates almost without errors, with no outside tool. It is still a slow experiment, but everything is online for anyone to see.
-
Block builds a speech model that learned to talk just by listening to conversations
Block, Jack Dorsey's company, has shown Dessa: an AI model that learned to talk without any text, only from recordings of conversations. It listens and speaks at the same time and runs on a powerful laptop. A small group of safety researchers is now the first to test it.
-
Nvidia releases free speech model that transcribes recordings in 40 languages, translates them and recognises speakers
Nvidia has released an open speech model that transcribes, translates and shows who is speaking, all in one go. It uses only a small part of its computing power per step and runs on a single graphics card, without the cloud. For now, the performance figures come from Nvidia itself.
-
Free tools take the brakes off Nvidia graphics cards: up to twice as much AI computing power
Free open-source tools remove a brake that Nvidia built into the firmware of its GeForce graphics cards. For AI calculations, some cards become up to twice as fast. In practice the gain is smaller, and the tools are still experimental.
-
Hugging Face releases open AI model that lets researchers 'talk' to DNA
With Hugging Face's Carbon-X, researchers paste a piece of DNA into a chat and ask in plain language whether a change is likely to be harmful. The model is free and runs on a researcher's own computer. It is meant for research; the next step is testing in the lab.
-
Free coding model for the laptop was largely developed by AI itself
The AI company Recursive has released Flint, a free AI model that helps with programming and runs on an ordinary laptop. According to the company, its own research AI did a large part of the work: a first step towards AI that improves itself.
-
Large open AI model from DeepSeek now fits on a computer with 128 gigabytes of memory
DeepSeek's new open AI model is too big for an ordinary computer. The company Unsloth made a heavily reduced version that runs on a powerful laptop or mini computer with 128 gigabytes of memory. This costs some accuracy.
-
Nvidia releases open AI models for digital assistants on servers and laptops
Nvidia has released three new open AI models for assistants that carry out tasks on their own. The largest runs in companies' data centres; the smaller ones simply work on a laptop. According to Nvidia, the large model beats top models on specialist tasks after extra training.
-
Meta releases Muse Spark Open: a large AI model for programming that also runs on your own computers
Meta has released Muse Spark Open, a large AI model for programming and independent agent tasks that anyone can download. According to Meta, it is the strongest American open model so far, and it even runs on two Mac Studios.
