Twoody
Local LLM on Mac
Run an LLM locally on your Mac
A large language model can run entirely on your Mac: private, offline and free. What you need, which model to choose, and the simplest way to start. On a PC, Twoody also exists for Windows and Linux.
Why run an LLM on your Mac
The model answers and reads your files on the machine. Once the model is installed, it works without internet. There is no subscription, no quota, and no account needed. The trade-off: a model that fits a Mac is smaller than the largest online models — excellent for writing, summaries and your documents, less so for the hardest reasoning.
What you need
A Mac with Apple Silicon (M1 or later) runs models comfortably; an Intel Mac runs small ones, slowly, on its processor. Memory decides the model, as Twoody counts it: 8 GB for about 4 billion parameters, 16 GB for 8 billion, 24 GB for 14 billion, 32 to 36 GB for 24 to 35 billion at 4-bit, 64 GB for 70 billion.
Which model to choose
Qwen3.5 writes well in many languages at every size; Llama, Gemma, Mistral and gpt-oss are good alternatives. Start with the model that fits your memory comfortably: a larger one that makes your Mac swap is slower than a smaller one.
What Twoody does for you
- It suggests the model that suits your Mac and installs it in one click; its catalogue holds 57, each with the memory it needs.
- It reads your folders of documents, and its answers cite their sources, down to the page.
- It runs on Intel Macs as on Apple silicon, on macOS 13.3 or later; on Apple silicon, with macOS 14, it can also install MLX, Apple's engine. And it exists for Windows and Linux.
With Twoody, in three steps
-
1
Join the waitlist: Twoody is in private beta, on the Mac as on Windows and Linux, and we will write to you when it opens to you.
-
2
Install the model it suggests for your Mac, in one click: 3.5 GB for Qwen3.5 4B, 6.7 GB for the 9B.
-
3
Ask your first question — and turn Wi-Fi off if you like.
Frequently asked questions
Is running an LLM locally on a Mac free?
Yes: the open-weight models are free to download, and Twoody is free. The only cost is your Mac's memory and electricity.
How much memory do I need to run an LLM on a Mac?
8 GB for a small model such as Qwen3.5 4B, 16 GB for Qwen3.5 9B on a Mac with Apple silicon (32 GB on an Intel Mac), 24 GB for Qwen3.6 35B-A3B. In Twoody, each model of the catalogue says the memory it needs; the calculator shows what fits each Mac, and how fast.
Can I run a local LLM on an Intel Mac?
Yes, with Twoody, on macOS 13.3 or later: the model runs on the processor, so small models work, slowly.
Is a local LLM as good as ChatGPT?
For everyday writing and questions about your documents, often close enough; for the hardest questions, no. In exchange, it is private, offline and free.
Try Twoody before it opens to everyone.
The private beta is free, on Mac, Windows and Linux, and on iPhone and Android with Twoody on your computer. Leave your email to ask for an invitation: we will write to you when it is ready for you.