Twoody
Local LLM calculator
A local LLM on your Intel Mac
Some local AI apps run only on Apple silicon. Twoody also runs on Intel Macs with macOS 13.3 or later: the model runs on the processor, so small models work, slowly.
| Your computer | Memory | Strongest that runs comfortably | Writes | Suggested by Twoody by default |
|---|---|---|---|---|
Intel MacBook Air, MacBook Pro 13″ (2018–2020) |
8 GB | Qwen3.5 0.8B One click in Twoody | 17–50 tokens/s | Qwen3.5 4B (4 GB) Runs — close other apps |
| 16 GB | Gemma 4 E4B One click in Twoody | 5.7–10 tokens/s | Qwen3.5 4B (4.4 GB) | |
| 32 GB | Qwen3.6 35B-A3B One click in Twoody | 9.3–17 tokens/s | Qwen3.5 9B (7.9 GB) | |
Intel MacBook Pro 15″, 16″ (2018–2019) |
16 GB | Gemma 4 E4B One click in Twoody | 5.1–9.1 tokens/s | Qwen3.5 4B (4.4 GB) |
| 32 GB | Qwen3.6 35B-A3B One click in Twoody | 8.3–15 tokens/s | Qwen3.5 9B (7.9 GB) | |
| 64 GB | Qwen3-Next 80B-A3B Not in Twoody's catalogue | 6.1–11 tokens/s | Qwen3.5 9B (7.9 GB) | |
Intel iMac, Mac mini (2017–2020) |
8 GB | Qwen3.5 0.8B One click in Twoody | 16–48 tokens/s | Qwen3.5 4B (4 GB) Runs — close other apps |
| 16 GB | Gemma 4 E4B One click in Twoody | 5.5–9.7 tokens/s | Qwen3.5 4B (4.4 GB) | |
| 32 GB | Qwen3.6 35B-A3B One click in Twoody | 8.8–16 tokens/s | Qwen3.5 9B (7.9 GB) | |
| 64 GB | Qwen3-Next 80B-A3B Not in Twoody's catalogue | 6.5–12 tokens/s | Qwen3.5 9B (7.9 GB) | |
iMac Pro, Mac Pro (2017–2019) |
32 GB | Qwen3.6 35B-A3B One click in Twoody | 19–34 tokens/s | Qwen3.5 9B (7.9 GB) |
| 64 GB | Qwen3-Next 80B-A3B Not in Twoody's catalogue | 14–26 tokens/s | Qwen3.5 9B (7.9 GB) | |
| 128 GB | Mistral Small 4 119B Not in Twoody's catalogue | 8.1–14 tokens/s | Qwen3.5 9B (7.9 GB) |
Speeds are estimates, not measurements made with Twoody, computed from public llama.cpp benchmarks. Figures reviewed on October 16, 2026.
How to read this table
One line per chip of this family and per memory size it comes with: the memory decides which models fit, the chip how fast they write.
- Strongest that runs comfortably
- The strongest model that fits comfortably there and writes at least at your reading speed, 5 tokens per second; under its name, whether it installs in one click in Twoody.
- Writes
- Its speed there, in tokens per second: an estimate from public llama.cpp benchmarks, not a measurement made with Twoody.
- Suggested by Twoody by default
- The model the app installs first on that computer, and the memory it needs there. Not always the strongest: one Twoody has measured with its memory, its tools and your documents.
Twoody is in private beta: leave your email to request access.
On an Intel Mac, llama.cpp uses the processor, not the graphics: a model of about 4 billion parameters writes a few words per second, enough for short answers.
On these Macs, Twoody suggests Qwen3.5 4B, the fastest on the processor, and the 9B from 32 GB.
MLX, Apple's engine, runs only on Apple silicon: on an Intel Mac, Twoody runs the model with llama.cpp, on macOS 13.3 or later.
Questions about running an LLM locally
Is there a local AI app for an Intel Mac?
Yes, in the private beta: Twoody runs on Intel Macs with macOS 13.3 or later, with an installer made for Intel. It installs a model in one click and runs it on the processor with llama.cpp; MLX, Apple's engine, needs Apple silicon. Leave your email to join the waitlist.
Does a local LLM work on an Intel Mac?
Yes, on the processor. Twoody suggests Qwen3.5 4B by default, which needs 4–4.4 GB of memory there: one of the models it has measured with its memory, its tools and your documents. Reading a long document takes minutes there.
Which local AI app works on macOS Ventura?
Twoody runs on macOS 13.3 (Ventura) and later, on Apple Silicon and Intel; it installs a model in one click.
Which model for an Intel Mac?
With 16 GB, the strongest model that runs comfortably there is Gemma 4 E4B, which writes 5.1–10 tokens/s depending on the Mac. It installs in one click from Twoody's catalogue. Twoody suggests Qwen3.5 4B by default, which needs 4.4 GB of memory there: one of the models it has measured with its memory, its tools and your documents. Larger models fit in memory but write more slowly than you read.
How fast is a local LLM on a MacBook Pro with an Intel Core i9 and 16 GB?
The 15″ and 16″ MacBook Pro of 2018–2019 have a Core i7 or i9 processor, which runs the model. The strongest model that runs comfortably there is Gemma 4 E4B, which writes 5.1–9.1 tokens/s. It installs in one click from Twoody's catalogue. Twoody suggests Qwen3.5 4B by default, which needs 4.4 GB of memory there: one of the models it has measured with its memory, its tools and your documents.
The best local LLM, by computer
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.