Local LLM on the Mac mini M1: best models and tokens/s

The best local LLM for the Mac mini M1, by memory

Memory	Strongest that runs comfortably	Writes	Suggested by Twoody by default
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.

“Strongest that runs comfortably”: the strongest model that fits comfortably in this memory and writes at least at your reading speed (5 tokens per second). “Suggested by Twoody by default”: the model the app installs first on this Mac, and the memory it needs there.

Twoody is in private beta: leave your email to request access.

Every model that runs well on the Mac mini M1 with 16 GB

31 of the 62 models the calculator knows (Twoody's catalogue and a few larger ones) run well here, the strongest first: the memory Twoody's app says each one needs on this computer, how fast it writes, and how long it takes to read a document.

Model	Memory	Writes	Reads a document
Gemma 4 12B One click in Twoody	Needs 7.6 GB of memory Runs comfortably	6.3–9 tokens/s	20 pages in 4 min
GLM-4.6V Flash One click in Twoody	Needs 7.9 GB of memory Runs comfortably	7.2–10 tokens/s	20 pages in 3 min
Qwen3.5 9B One click in Twoody	Needs 7.4 GB of memory Runs comfortably	5.4–11 tokens/s	20 pages in 3 min
GLM-4 9B One click in Twoody	Needs 6.7 GB of memory Runs comfortably	7.2–10 tokens/s	20 pages in 3 min
Ministral 3 8B One click in Twoody	Needs 8.4 GB of memory Runs comfortably	8.4–12 tokens/s	20 pages in 3 min
Granite 4.1 8B One click in Twoody	Needs 8 GB of memory Runs comfortably	7.9–11 tokens/s	20 pages in 3 min
Qwen3 8B One click in Twoody	Needs 7.2 GB of memory Runs comfortably	8.7–12 tokens/s	20 pages in 3 min
Llama 3.1 8B One click in Twoody	Needs 6.9 GB of memory Runs comfortably	8.9–13 tokens/s	20 pages in 3 min
Olmo 3 7B One click in Twoody	Needs 8.2 GB of memory Runs comfortably	9–13 tokens/s	20 pages in 2 min
Gemma 4 E4B One click in Twoody	Needs 6.6 GB of memory Runs comfortably	15–21 tokens/s	20 pages in 86 s
Qwen3.5 4B One click in Twoody	Needs 4.4 GB of memory Runs comfortably	11–22 tokens/s	20 pages in 2 min
Qwen3 4B Instruct 2507 One click in Twoody	Needs 4.9 GB of memory Runs comfortably	16–24 tokens/s	20 pages in 76 s
Nemotron 3 Nano 4B One click in Twoody	Needs 3.3 GB of memory Runs comfortably	10–21 tokens/s	20 pages in 78 s
Ministral 3 3B One click in Twoody	Needs 5 GB of memory Runs comfortably	19–28 tokens/s	20 pages in 73 s
Phi-4 mini One click in Twoody	Needs 4.6 GB of memory Runs comfortably	17–24 tokens/s	20 pages in 73 s
Llama 3.2 3B One click in Twoody	Needs 3.9 GB of memory Runs comfortably	20–29 tokens/s	20 pages in 61 s
Gemma 4 E2B One click in Twoody	Needs 4.7 GB of memory Runs comfortably	27–39 tokens/s	20 pages in 44 s
Qwen3.5 2B One click in Twoody	Needs 2.7 GB of memory Runs comfortably	21–42 tokens/s	20 pages in 45 s
Qwen3.5 0.8B One click in Twoody	Needs 1.5 GB of memory Runs comfortably	35–105 tokens/s	20 pages in 18 s
DeepSeek-Coder-V2 Lite One click in Twoody	Needs 10.4 GB of memory Runs — close other apps	23–33 tokens/s	20 pages in 58 s
Ministral 3 14B Reasoning One click in Twoody	Needs 10.5 GB of memory Runs — close other apps	5.4–7.8 tokens/s	20 pages in 4 min
GLM-Z1 9B One click in Twoody	Needs 6.7 GB of memory Runs comfortably	7.2–10 tokens/s	20 pages in 3 min
DeepSeek-R1 8B One click in Twoody	Needs 7.2 GB of memory Runs comfortably	8.7–12 tokens/s	20 pages in 3 min
DeepSeek-R1 Distill Llama 8B One click in Twoody	Needs 6.9 GB of memory Runs comfortably	8.9–13 tokens/s	20 pages in 3 min
DeepSeek-R1 Distill Qwen 7B One click in Twoody	Needs 5.5 GB of memory Runs comfortably	9.5–14 tokens/s	20 pages in 2 min
Qwen3 4B Thinking 2507 One click in Twoody	Needs 4.9 GB of memory Runs comfortably	16–24 tokens/s	20 pages in 76 s
Phi-4 mini reasoning One click in Twoody	Needs 4.6 GB of memory Runs comfortably	17–24 tokens/s	20 pages in 73 s
SmolLM3 3B One click in Twoody	Needs 3.2 GB of memory Runs comfortably	21–31 tokens/s	20 pages in 59 s
LFM2.5 2.6B One click in Twoody	Needs 2.1 GB of memory Runs comfortably	17–35 tokens/s	20 pages in 53 s
MiniCPM5 2B One click in Twoody	Needs 2.5 GB of memory Runs comfortably	25–36 tokens/s	20 pages in 48 s
Llama 3.2 1B One click in Twoody	Needs 1.6 GB of memory Runs comfortably	32–95 tokens/s	20 pages in 23 s

Besides these, 6 models would run partly on the processor, much slower, and 25 are too big for this computer. See them all in the calculator.

Each model's memory is what Twoody shows in “Models” for this computer: the same formula, the same files (the one for reading images included), the same conversation length — catalogue checked on October 15, 2026.

Mac mini M1 compared with Mac mini M2, Mac mini M4, Mac mini M6 and Mac mini M4 Pro

Computer	Memory	Qwen3.5 9B writes	Reads a document	Strongest that runs comfortably
Mac mini M1	16 GB	5.4–11 tokens/s	20 pages in 3 min	Gemma 4 12B 6.3–9 tokens/s
Mac mini M2	16 GB	8.1–16 tokens/s	20 pages in 2 min	Gemma 4 12B 9.5–14 tokens/s
Mac mini M4	16 GB	9.3–19 tokens/s	20 pages in 2 min	Gemma 4 12B 11–15 tokens/s
Mac mini M6	16 GB	13–23 tokens/s	20 pages in 25 s	Gemma 4 12B 12–22 tokens/s
Mac mini M4 Pro	24 GB	20–39 tokens/s	20 pages in 56 s	Qwen3 14B 18–27 tokens/s

Memory decides which models fit; the chip, how fast they write. Each Mac is shown with 16 GB, or the nearest size it comes with.

This Mac comes with 8 or 16 GB of memory, shared between its processor and its graphics, which may use most of it: that memory decides which models fit, and it cannot be added later.

It reads its memory at 68 GB/s. Speed follows that bandwidth more than the processor: that is why a Pro, Max or Ultra chip writes faster with the same model.

Twoody is in private beta on Macs with Apple silicon with macOS 13.3 or later: it suggests the model that suits this Mac, installs it in one click and runs it with llama.cpp; with macOS 14, it can also install MLX, Apple's engine.

Questions about running an LLM locally

Which local LLM for the Mac mini M1 with 16 GB?

The strongest model that runs comfortably there is Gemma 4 12B, which writes 6.3–9 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.

How much memory does the Mac mini M1 need for a local LLM?

The strongest models that run comfortably there, by memory: with 8 GB, Qwen3.5 4B (11–22 tokens/s, one click in Twoody); with 16 GB, Gemma 4 12B (6.3–9 tokens/s, one click in Twoody). A Mac's memory cannot be added later: choose it for the models you want to run.

How many tokens per second does the Mac mini M1 write?

With Qwen3.5 9B, the model Twoody suggests there, it writes 5.4–11 tokens/s and reads a document of about 20 pages in 3 min. These speeds are estimates from public llama.cpp benchmarks, not measurements made with Twoody.

How does the Mac mini M1 compare with the Mac mini M2, Mac mini M4, Mac mini M6 and Mac mini M4 Pro?

With Qwen3.5 9B, the model Twoody suggests: Mac mini M1, 5.4–11 tokens/s; Mac mini M2, 8.1–16 tokens/s; Mac mini M4, 9.3–19 tokens/s; Mac mini M6, 13–23 tokens/s; Mac mini M4 Pro, 20–39 tokens/s. Memory decides which models fit; the chip, how fast they write.

Does Twoody run on the Mac mini M1?

Yes, in the private beta, with macOS 13.3 or later: Twoody suggests the model that suits it, installs it in one click and runs it on the Mac's graphics with llama.cpp. Leave your email to join the waitlist.

Other computers and guides

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.

Request beta access

A local LLM on the Mac mini M1