← Everything the Apple M2 Max runsApple M2 Max · Llama 3.3 70B

Can the Apple M2 Max run Llama 3.3 70B?

Yes, with 64 GB or more. Llama 3.3 70B needs about 45 GB and the Apple M2 Max with 64 GB of unified memory leaves about 48 GB for models. Expect about 5 tok/s, slow, but it works. The 32 GB version doesn't have room.

ollama run llama3.3:70b

First time? Install Ollama, then paste that into a terminal.

Llama 3.3 70B needsAbout 45 GB
Apple M2 Max has32 or 64 or 96 GB unified memory
Bandwidth400 GB/s
Estimated speed~5 tok/s
By memory size

Each Apple M2 Max version

  • 32 GB (about 21 GB usable)Too big
  • 64 GB (about 48 GB usable)Slow ~5 tok/s
  • 96 GB (about 72 GB usable)Slow ~5 tok/s
Want it faster?

Speed comes from memory bandwidth: the card reads all 43 GB of active weights for every token. On the Apple M2 Max, gpt-oss 120B runs at about 48 tok/s if you can trade some quality for speed. Cards that run Llama 3.3 70B faster:

How we estimate

Speed is roughly memory bandwidth divided by the weights read per token, calibrated on our own rack. Sizes are Ollama's default 4-bit downloads plus about 1.2 GB for context. Real results are usually within about a third. Measured it yourself? Send us the number.

Keep going

More about the Apple M2 Max and Llama 3.3 70B