Local LLM on the Mac mini M6: best models and tokens/s

The best local LLM for the Mac mini M6, by memory

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

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 M6 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	12–22 tokens/s	20 pages in 30 s
GLM-4.6V Flash One click in Twoody	Needs 7.9 GB of memory Runs comfortably	14–25 tokens/s	20 pages in 26 s
Qwen3.5 9B One click in Twoody	Needs 7.4 GB of memory Runs comfortably	13–23 tokens/s	20 pages in 25 s
GLM-4 9B One click in Twoody	Needs 6.7 GB of memory Runs comfortably	14–25 tokens/s	20 pages in 24 s
Ministral 3 8B One click in Twoody	Needs 8.4 GB of memory Runs comfortably	16–29 tokens/s	20 pages in 22 s
Granite 4.1 8B One click in Twoody	Needs 8 GB of memory Runs comfortably	15–27 tokens/s	20 pages in 22 s
Qwen3 8B One click in Twoody	Needs 7.2 GB of memory Runs comfortably	17–30 tokens/s	20 pages in 21 s
Llama 3.1 8B One click in Twoody	Needs 6.9 GB of memory Runs comfortably	17–31 tokens/s	20 pages in 20 s
Olmo 3 7B One click in Twoody	Needs 8.2 GB of memory Runs comfortably	17–31 tokens/s	20 pages in 18 s
Gemma 4 E4B One click in Twoody	Needs 6.6 GB of memory Runs comfortably	28–50 tokens/s	20 pages in 11 s
Qwen3.5 4B One click in Twoody	Needs 4.4 GB of memory Runs comfortably	25–45 tokens/s	20 pages in 12 s
Qwen3 4B Instruct 2507 One click in Twoody	Needs 4.9 GB of memory Runs comfortably	31–56 tokens/s	20 pages in 10 s
Nemotron 3 Nano 4B One click in Twoody	Needs 3.3 GB of memory Runs comfortably	24–44 tokens/s	20 pages in 10 s
Ministral 3 3B One click in Twoody	Needs 5 GB of memory Runs comfortably	37–66 tokens/s	20 pages in 10 s
Phi-4 mini One click in Twoody	Needs 4.6 GB of memory Runs comfortably	32–57 tokens/s	20 pages in 10 s
Llama 3.2 3B One click in Twoody	Needs 3.9 GB of memory Runs comfortably	39–69 tokens/s	20 pages in 8 s
Gemma 4 E2B One click in Twoody	Needs 4.7 GB of memory Runs comfortably	51–91 tokens/s	20 pages in 6 s
Qwen3.5 2B One click in Twoody	Needs 2.7 GB of memory Runs comfortably	49–87 tokens/s	20 pages in 6 s
Qwen3.5 0.8B One click in Twoody	Needs 1.5 GB of memory Runs comfortably	72–216 tokens/s	20 pages in 2 s
DeepSeek-Coder-V2 Lite One click in Twoody	Needs 10.4 GB of memory Runs — close other apps	44–78 tokens/s	20 pages in 8 s
Ministral 3 14B Reasoning One click in Twoody	Needs 10.5 GB of memory Runs — close other apps	10–19 tokens/s	20 pages in 35 s
GLM-Z1 9B One click in Twoody	Needs 6.7 GB of memory Runs comfortably	14–25 tokens/s	20 pages in 24 s
DeepSeek-R1 8B One click in Twoody	Needs 7.2 GB of memory Runs comfortably	17–30 tokens/s	20 pages in 21 s
DeepSeek-R1 Distill Llama 8B One click in Twoody	Needs 6.9 GB of memory Runs comfortably	17–31 tokens/s	20 pages in 20 s
DeepSeek-R1 Distill Qwen 7B One click in Twoody	Needs 5.5 GB of memory Runs comfortably	18–33 tokens/s	20 pages in 19 s
Qwen3 4B Thinking 2507 One click in Twoody	Needs 4.9 GB of memory Runs comfortably	31–56 tokens/s	20 pages in 10 s
Phi-4 mini reasoning One click in Twoody	Needs 4.6 GB of memory Runs comfortably	32–57 tokens/s	20 pages in 10 s
SmolLM3 3B One click in Twoody	Needs 3.2 GB of memory Runs comfortably	40–72 tokens/s	20 pages in 8 s
LFM2.5 2.6B One click in Twoody	Needs 2.1 GB of memory Runs comfortably	40–72 tokens/s	20 pages in 7 s
MiniCPM5 2B One click in Twoody	Needs 2.5 GB of memory Runs comfortably	46–82 tokens/s	20 pages in 6 s
Llama 3.2 1B One click in Twoody	Needs 1.6 GB of memory Runs comfortably	68–203 tokens/s	20 pages in 3 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 M6 compared with Mac mini M4, Mac mini M4 Pro, Mac mini M5 Pro and Mac mini M1

Computer	Memory	Qwen3.5 9B writes	Reads a document	Strongest that runs comfortably
Mac mini M6	16 GB	13–23 tokens/s	20 pages in 25 s	Gemma 4 12B 12–22 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 M4 Pro	24 GB	20–39 tokens/s	20 pages in 56 s	Qwen3 14B 18–27 tokens/s
Mac mini M5 Pro	24 GB	24–49 tokens/s	20 pages in 17 s	Qwen3 14B 22–32 tokens/s
Mac mini M1	16 GB	5.4–11 tokens/s	20 pages in 3 min	Gemma 4 12B 6.3–9 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 16, 24 or 32 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 153 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 M6 with 16 GB?

The strongest model that runs comfortably there is Gemma 4 12B, which writes 12–22 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 M6 need for a local LLM?

The strongest models that run comfortably there, by memory: with 16 GB, Gemma 4 12B (12–22 tokens/s, one click in Twoody); with 24 GB, Qwen3 14B (10–19 tokens/s, one click in Twoody); with 32 GB, Qwen3.6 35B-A3B (41–73 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 M6 write?

With Qwen3.5 9B, the model Twoody suggests there, it writes 13–23 tokens/s and reads a document of about 20 pages in 25 s. These speeds are estimates from public llama.cpp benchmarks, not measurements made with Twoody.

How does the Mac mini M6 compare with the Mac mini M4, Mac mini M4 Pro, Mac mini M5 Pro and Mac mini M1?

With Qwen3.5 9B, the model Twoody suggests: Mac mini M6, 13–23 tokens/s; Mac mini M4, 9.3–19 tokens/s; Mac mini M4 Pro, 20–39 tokens/s; Mac mini M5 Pro, 24–49 tokens/s; Mac mini M1, 5.4–11 tokens/s. Memory decides which models fit; the chip, how fast they write.

Does Twoody run on the Mac mini M6?

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 M6