Twoody

Local LLM calculator

The best local LLM for your MacBook Pro

From an M1 with 8 GB to an M5 Max with 128 GB: the strongest model that runs comfortably on each MacBook Pro, and how fast it writes.

Your computer Memory Recommended — runs comfortably Writes One click in Twoody

M5 Max — MacBook Pro, Mac Studio

 36 GB GLM-4.7-Flash 100+ tokens/s Qwen3 14B
48 GB GLM-4.7-Flash 100+ tokens/s Qwen3 14B
64 GB GLM-4.7-Flash 100+ tokens/s Qwen3 14B
128 GB Qwen3-Next 80B-A3B 96–193 tokens/s Qwen3 14B

M5 Pro — MacBook Pro, Mac mini

 24 GB gpt-oss-20b 68–97 tokens/s Qwen3 14B
48 GB GLM-4.7-Flash 92–132 tokens/s Qwen3 14B
64 GB GLM-4.7-Flash 92–132 tokens/s Qwen3 14B

M5 — MacBook Air, MacBook Pro

 16 GB Llama 3.1 8B 20–28 tokens/s Qwen3 8B
24 GB gpt-oss-20b 32–47 tokens/s Qwen3 14B
32 GB GLM-4.7-Flash 41–59 tokens/s Qwen3 14B

M4 Max — MacBook Pro, Mac Studio

 36 GB GLM-4.7-Flash 73–106 tokens/s Qwen3 14B
48 GB gpt-oss-20b 85–122 tokens/s Qwen3 14B
64 GB gpt-oss-20b 85–122 tokens/s Qwen3 14B
128 GB Qwen3-Next 80B-A3B 53–107 tokens/s Qwen3 14B

M4 Pro — MacBook Pro, Mac mini

 24 GB gpt-oss-20b 52–74 tokens/s Qwen3 14B
48 GB GLM-4.7-Flash 56–81 tokens/s Qwen3 14B
64 GB GLM-4.7-Flash 56–81 tokens/s Qwen3 14B

M4 — MacBook Air, MacBook Pro, Mac mini, iMac

 16 GB Llama 3.1 8B 15–22 tokens/s Qwen3 8B
24 GB gpt-oss-20b 25–36 tokens/s Qwen3 14B
32 GB GLM-4.7-Flash 32–46 tokens/s Qwen3 14B

M3 Max — MacBook Pro

 36 GB GLM-4.7-Flash 68–97 tokens/s Qwen3 14B
48 GB gpt-oss-20b 68–98 tokens/s Qwen3 14B
64 GB gpt-oss-20b 68–98 tokens/s Qwen3 14B
96 GB Qwen3-Next 80B-A3B 47–93 tokens/s Qwen3 14B
128 GB Qwen3-Next 80B-A3B 46–93 tokens/s Qwen3 14B

M3 Pro — MacBook Pro

 18 GB Llama 3.1 8B 19–28 tokens/s Qwen3 8B
36 GB GLM-4.7-Flash 42–60 tokens/s Qwen3 14B

M3 — MacBook Air, MacBook Pro, iMac

 8 GB Llama 3.2 3B 31–45 tokens/s Qwen3 4B
16 GB Llama 3.1 8B 13–19 tokens/s Qwen3 8B
24 GB gpt-oss-20b 23–32 tokens/s Qwen3 14B

M2 Max — MacBook Pro, Mac Studio

 32 GB gpt-oss-20b 62–90 tokens/s Qwen3 14B
64 GB gpt-oss-20b 62–90 tokens/s Qwen3 14B
96 GB Qwen3-Next 80B-A3B 39–78 tokens/s Qwen3 14B

M2 Pro — MacBook Pro, Mac mini

 16 GB Llama 3.1 8B 24–35 tokens/s Qwen3 8B
32 GB GLM-4.7-Flash 45–65 tokens/s Qwen3 14B

M2 — MacBook Air, MacBook Pro, Mac mini

 8 GB Llama 3.2 3B 32–45 tokens/s Qwen3 4B
16 GB Llama 3.1 8B 13–19 tokens/s Qwen3 8B
24 GB gpt-oss-20b 23–33 tokens/s Qwen3 14B

M1 Max — MacBook Pro, Mac Studio

 32 GB gpt-oss-20b 56–80 tokens/s Qwen3 14B
64 GB gpt-oss-20b 56–80 tokens/s Qwen3 14B

M1 Pro — MacBook Pro

 16 GB Llama 3.1 8B 23–33 tokens/s Qwen3 8B
32 GB GLM-4.7-Flash 39–56 tokens/s Qwen3 14B

M1 — MacBook Air, MacBook Pro, Mac mini, iMac

 8 GB Llama 3.2 3B 20–29 tokens/s Qwen3 4B
16 GB Llama 3.1 8B 8.9–13 tokens/s Qwen3 8B

Estimates, not measurements, computed from public llama.cpp benchmarks. Figures reviewed on September 26, 2026.

Memory decides the size of the model: 16 GB for 8 billion parameters, 32 to 48 GB for mixtures of experts such as Qwen3 30B-A3B, 64 GB and more for 70-billion models.

The Pro and Max chips read their memory two to five times faster than the base chips: that is what makes them write fast with large models.

With its fans, a MacBook Pro keeps its speed through long sessions, on battery as on power.

Local LLM calculator

Questions about running an LLM locally

Which LLM for a MacBook Pro with an M4 Max?

With 64 GB or more, gpt-oss-120b (on 128 GB), Llama 3.3 70B or Qwen3 30B-A3B; the mixtures of experts write several times faster than the dense 70B.

What does 48 GB change on a MacBook Pro?

It runs mixtures of experts such as Qwen3 30B-A3B or gpt-oss-20b comfortably, at several dozen tokens per second, with room for your other apps.

Does a local LLM drain a MacBook Pro's battery?

Writing an answer uses the graphics at full power for a few seconds; between answers the model waits without using any. Long document work on battery is fine; hours of continuous writing are not.

The best local LLM, by computer

Try local AI on your Mac, for free.

Version 0.11.5 · macOS 13 or later · no account, no subscription. Download it, install a model in one click, and ask your first question — even offline.

Download for Apple Silicon Mac Intel Mac