Local LLM on the iMac M4: best models and tokens/s

The best local LLM for the iMac M4, by memory

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

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 iMac M4 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	11–15 tokens/s	20 pages in 2 min
GLM-4.6V Flash One click in Twoody	Needs 7.9 GB of memory Runs comfortably	12–18 tokens/s	20 pages in 2 min
Qwen3.5 9B One click in Twoody	Needs 7.4 GB of memory Runs comfortably	9.3–19 tokens/s	20 pages in 2 min
GLM-4 9B One click in Twoody	Needs 6.7 GB of memory Runs comfortably	12–18 tokens/s	20 pages in 87 s
Ministral 3 8B One click in Twoody	Needs 8.4 GB of memory Runs comfortably	14–21 tokens/s	20 pages in 83 s
Granite 4.1 8B One click in Twoody	Needs 8 GB of memory Runs comfortably	13–19 tokens/s	20 pages in 82 s
Qwen3 8B One click in Twoody	Needs 7.2 GB of memory Runs comfortably	15–21 tokens/s	20 pages in 76 s
Llama 3.1 8B One click in Twoody	Needs 6.9 GB of memory Runs comfortably	15–22 tokens/s	20 pages in 74 s
Olmo 3 7B One click in Twoody	Needs 8.2 GB of memory Runs comfortably	15–22 tokens/s	20 pages in 68 s
Gemma 4 E4B One click in Twoody	Needs 6.6 GB of memory Runs comfortably	25–35 tokens/s	20 pages in 42 s
Qwen3.5 4B One click in Twoody	Needs 4.4 GB of memory Runs comfortably	18–37 tokens/s	20 pages in 45 s
Qwen3 4B Instruct 2507 One click in Twoody	Needs 4.9 GB of memory Runs comfortably	28–40 tokens/s	20 pages in 37 s
Nemotron 3 Nano 4B One click in Twoody	Needs 3.3 GB of memory Runs comfortably	18–35 tokens/s	20 pages in 38 s
Ministral 3 3B One click in Twoody	Needs 5 GB of memory Runs comfortably	33–47 tokens/s	20 pages in 35 s
Phi-4 mini One click in Twoody	Needs 4.6 GB of memory Runs comfortably	28–40 tokens/s	20 pages in 35 s
Llama 3.2 3B One click in Twoody	Needs 3.9 GB of memory Runs comfortably	34–49 tokens/s	20 pages in 30 s
Gemma 4 E2B One click in Twoody	Needs 4.7 GB of memory Runs comfortably	44–64 tokens/s	20 pages in 21 s
Qwen3.5 2B One click in Twoody	Needs 2.7 GB of memory Runs comfortably	35–70 tokens/s	20 pages in 22 s
Qwen3.5 0.8B One click in Twoody	Needs 1.5 GB of memory Runs comfortably	54–163 tokens/s	20 pages in 9 s
DeepSeek-Coder-V2 Lite One click in Twoody	Needs 10.4 GB of memory Runs — close other apps	38–55 tokens/s	20 pages in 28 s
Ministral 3 14B Reasoning One click in Twoody	Needs 10.5 GB of memory Runs — close other apps	9.3–13 tokens/s	20 pages in 2 min
GLM-Z1 9B One click in Twoody	Needs 6.7 GB of memory Runs comfortably	12–18 tokens/s	20 pages in 87 s
DeepSeek-R1 8B One click in Twoody	Needs 7.2 GB of memory Runs comfortably	15–21 tokens/s	20 pages in 76 s
DeepSeek-R1 Distill Llama 8B One click in Twoody	Needs 6.9 GB of memory Runs comfortably	15–22 tokens/s	20 pages in 74 s
DeepSeek-R1 Distill Qwen 7B One click in Twoody	Needs 5.5 GB of memory Runs comfortably	16–24 tokens/s	20 pages in 71 s
Qwen3 4B Thinking 2507 One click in Twoody	Needs 4.9 GB of memory Runs comfortably	28–40 tokens/s	20 pages in 37 s
Phi-4 mini reasoning One click in Twoody	Needs 4.6 GB of memory Runs comfortably	28–40 tokens/s	20 pages in 35 s
SmolLM3 3B One click in Twoody	Needs 3.2 GB of memory Runs comfortably	35–51 tokens/s	20 pages in 29 s
LFM2.5 2.6B One click in Twoody	Needs 2.1 GB of memory Runs comfortably	29–58 tokens/s	20 pages in 26 s
MiniCPM5 2B One click in Twoody	Needs 2.5 GB of memory Runs comfortably	40–58 tokens/s	20 pages in 23 s
Llama 3.2 1B One click in Twoody	Needs 1.6 GB of memory Runs comfortably	52–156 tokens/s	20 pages in 11 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.

iMac M4 compared with iMac M3 and iMac M1

Computer	Memory	Qwen3.5 9B writes	Reads a document	Strongest that runs comfortably
iMac M4	16 GB	9.3–19 tokens/s	20 pages in 2 min	Gemma 4 12B 11–15 tokens/s
iMac M3	16 GB	8–16 tokens/s	20 pages in 2 min	Gemma 4 12B 9.4–14 tokens/s
iMac 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 120 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 iMac 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.

How much memory does the iMac M4 need for a local LLM?

The strongest models that run comfortably there, by memory: with 16 GB, Gemma 4 12B (11–15 tokens/s, one click in Twoody); with 24 GB, Qwen3 14B (8.6–12 tokens/s, one click in Twoody); with 32 GB, Qwen3.6 35B-A3B (30–59 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 iMac M4 write?

With Qwen3.5 9B, the model Twoody suggests there, it writes 9.3–19 tokens/s and reads a document of about 20 pages in 2 min. These speeds are estimates from public llama.cpp benchmarks, not measurements made with Twoody.

How does the iMac M4 compare with the iMac M3 and iMac M1?

With Qwen3.5 9B, the model Twoody suggests: iMac M4, 9.3–19 tokens/s; iMac M3, 8–16 tokens/s; iMac M1, 5.4–11 tokens/s. Memory decides which models fit; the chip, how fast they write.

Does Twoody run on the iMac M4?

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 iMac M4