Twoody
Local LLM calculator
The best local LLM for your Mac mini
From the M1 to the M6, and the Pro versions: the strongest model that runs comfortably on each Mac mini, and how fast it writes.
| Your computer | Memory | Strongest that runs comfortably | Writes | Suggested by Twoody by default |
|---|---|---|---|---|
M5 Pro — MacBook Pro, Mac mini |
24 GB | Qwen3 14B One click in Twoody | 22–32 tokens/s | Qwen3.5 9B (7.4 GB) |
| 48 GB | Qwen3.6 35B-A3B One click in Twoody | 87–174 tokens/s | Qwen3.5 9B (7.9 GB) | |
| 64 GB | Qwen3-Next 80B-A3B Not in Twoody's catalogue | 65–129 tokens/s | Qwen3.5 9B (7.9 GB) | |
M6 — Mac mini |
16 GB | Gemma 4 12B One click in Twoody | 12–22 tokens/s | Qwen3.5 9B (7.4 GB) |
| 24 GB | Qwen3 14B One click in Twoody | 10–19 tokens/s | Qwen3.5 9B (7.4 GB) | |
| 32 GB | Qwen3.6 35B-A3B One click in Twoody | 41–73 tokens/s | Qwen3.5 9B (7.9 GB) | |
M4 Pro — MacBook Pro, Mac mini |
24 GB | Qwen3 14B One click in Twoody | 18–27 tokens/s | Qwen3.5 9B (7.4 GB) |
| 48 GB | Qwen3.6 35B-A3B One click in Twoody | 51–102 tokens/s | Qwen3.5 9B (7.9 GB) | |
| 64 GB | Qwen3-Next 80B-A3B Not in Twoody's catalogue | 39–79 tokens/s | Qwen3.5 9B (7.9 GB) | |
M4 — MacBook Air, MacBook Pro, Mac mini, iMac |
16 GB | Gemma 4 12B One click in Twoody | 11–15 tokens/s | Qwen3.5 9B (7.4 GB) |
| 24 GB | Qwen3 14B One click in Twoody | 8.6–12 tokens/s | Qwen3.5 9B (7.4 GB) | |
| 32 GB | Qwen3.6 35B-A3B One click in Twoody | 30–59 tokens/s | Qwen3.5 9B (7.9 GB) | |
M2 Pro — MacBook Pro, Mac mini |
16 GB | Gemma 4 12B One click in Twoody | 17–25 tokens/s | Qwen3.5 9B (7.4 GB) |
| 32 GB | Qwen3.6 35B-A3B One click in Twoody | 42–83 tokens/s | Qwen3.5 9B (7.9 GB) | |
M2 — MacBook Air, MacBook Pro, Mac mini |
8 GB | Qwen3.5 4B One click in Twoody | 17–33 tokens/s | Qwen3.5 4B (4 GB) |
| 16 GB | Gemma 4 12B One click in Twoody | 9.5–14 tokens/s | Qwen3.5 9B (7.4 GB) | |
| 24 GB | Qwen3 14B One click in Twoody | 7.4–11 tokens/s | Qwen3.5 9B (7.4 GB) | |
M1 — MacBook Air, MacBook Pro, Mac mini, iMac |
8 GB | Qwen3.5 4B One click in Twoody | 11–22 tokens/s | Qwen3.5 4B (4 GB) |
| 16 GB | Gemma 4 12B One click in Twoody | 6.3–9 tokens/s | Qwen3.5 9B (7.4 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.
The Mac mini is the least expensive way to run a local LLM on a Mac: a model of 8 billion parameters with 16 GB, a mixture of experts with 48 GB and a Pro chip.
Silent and always on, a Mac mini is also the kind of computer the iPhone and Android apps, in private beta, are made to use from afar.
The Pro versions read their memory more than twice as fast as the base chips: larger models, and faster answers.
Questions about running an LLM locally
Which LLM for a Mac mini M4 with 16 GB?
The strongest model that runs comfortably there is Gemma 4 12B, which writes 11–15 tokens/s. It installs in one click from Twoody's catalogue. Twoody suggests Qwen3.5 9B by default, which needs 7.4 GB of memory there: one of the models it has measured with its memory, its tools and your documents.
Is a Mac mini M4 Pro worth it for local AI?
Yes. The strongest models that run comfortably there, by memory: with 24 GB, Qwen3 14B (18–27 tokens/s, one click in Twoody); with 48 GB, Qwen3.6 35B-A3B (51–102 tokens/s, one click in Twoody); with 64 GB, Qwen3-Next 80B-A3B (39–79 tokens/s, not in Twoody's catalogue). Twoody suggests Qwen3.5 9B by default, which needs 7.4–7.9 GB of memory there: one of the models it has measured with its memory, its tools and your documents.
Can a Mac mini serve a local LLM to other devices?
That is what the iPhone and Android apps, in private beta, do: they use the model of your Mac from the phone.
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.