← Every GPUApple · 64 or 128 or 192 GB unified memory · 800 GB/s

What can the Apple M2 Ultra run?

With 64 GB, 9 of 12 popular open models fit. The best pick is Qwen3 32B at about 22 tok/s, about reading speed.

ollama run qwen3:32b

First time? Install Ollama, then paste that into a terminal. Is this your machine? Check it on the homepage.

64 GB unified memory · about 48 GB for models

Every model the Apple M2 Ultra 64 GB can run

9 of 12 fit. Best pick: Qwen3 32B.

  • Qwen3 4BQuick everyday chat and summaries
    ~180 tok/s
    Runs greatqwen3:4b
  • Qwen3 8BA solid all-rounder for chat and writing
    ~85 tok/s
    Runs greatqwen3:8b
  • Gemma 3 12BReads images as well as text
    ~54 tok/s
    Runs greatgemma3:12b
  • Qwen3 14BNoticeably smarter at reasoning and code
    ~47 tok/s
    Runs greatqwen3:14b
  • gpt-oss 20BOpenAI's open model. Fast, strong reasoning
    ~140 tok/s
    Runs greatgpt-oss:20b
  • Gemma 3 27BGoogle's best open model for its size
    ~26 tok/s
    Usablegemma3:27b
  • Qwen3 30B-A3B30B smarts at small-model speed
    ~140 tok/s
    Runs greatqwen3:30b
  • Qwen3 32BStrong coding and long answers
    ~22 tok/s
    Usableqwen3:32b
  • Llama 3.3 70BClose to the big cloud models
    ~10 tok/s
    Usablellama3.3:70b
  • gpt-oss 120BOpenAI's largest open model
    needs 67 GB
    Too biggpt-oss:120b
  • Qwen3 235B-A22BAlibaba's flagship open model, for multi-GPU rigs
    needs 144 GB
    Too bigqwen3:235b
  • DeepSeek R1 671BThe full DeepSeek R1, for the biggest rigs
    needs 406 GB
    Too bigdeepseek-r1:671b
128 GB unified memory · about 96 GB for models

Every model the Apple M2 Ultra 128 GB can run

10 of 12 fit. Best pick: gpt-oss 120B.

  • Qwen3 4BQuick everyday chat and summaries
    ~180 tok/s
    Runs greatqwen3:4b
  • Qwen3 8BA solid all-rounder for chat and writing
    ~85 tok/s
    Runs greatqwen3:8b
  • Gemma 3 12BReads images as well as text
    ~54 tok/s
    Runs greatgemma3:12b
  • Qwen3 14BNoticeably smarter at reasoning and code
    ~47 tok/s
    Runs greatqwen3:14b
  • gpt-oss 20BOpenAI's open model. Fast, strong reasoning
    ~140 tok/s
    Runs greatgpt-oss:20b
  • Gemma 3 27BGoogle's best open model for its size
    ~26 tok/s
    Usablegemma3:27b
  • Qwen3 30B-A3B30B smarts at small-model speed
    ~140 tok/s
    Runs greatqwen3:30b
  • Qwen3 32BStrong coding and long answers
    ~22 tok/s
    Usableqwen3:32b
  • Llama 3.3 70BClose to the big cloud models
    ~10 tok/s
    Usablellama3.3:70b
  • gpt-oss 120BOpenAI's largest open model
    ~97 tok/s
    Runs greatgpt-oss:120b
  • Qwen3 235B-A22BAlibaba's flagship open model, for multi-GPU rigs
    needs 144 GB
    Too bigqwen3:235b
  • DeepSeek R1 671BThe full DeepSeek R1, for the biggest rigs
    needs 406 GB
    Too bigdeepseek-r1:671b
192 GB unified memory · about 144 GB for models

Every model the Apple M2 Ultra 192 GB can run

11 of 12 fit. Best pick: Qwen3 235B-A22B.

  • Qwen3 4BQuick everyday chat and summaries
    ~180 tok/s
    Runs greatqwen3:4b
  • Qwen3 8BA solid all-rounder for chat and writing
    ~85 tok/s
    Runs greatqwen3:8b
  • Gemma 3 12BReads images as well as text
    ~54 tok/s
    Runs greatgemma3:12b
  • Qwen3 14BNoticeably smarter at reasoning and code
    ~47 tok/s
    Runs greatqwen3:14b
  • gpt-oss 20BOpenAI's open model. Fast, strong reasoning
    ~140 tok/s
    Runs greatgpt-oss:20b
  • Gemma 3 27BGoogle's best open model for its size
    ~26 tok/s
    Usablegemma3:27b
  • Qwen3 30B-A3B30B smarts at small-model speed
    ~140 tok/s
    Runs greatqwen3:30b
  • Qwen3 32BStrong coding and long answers
    ~22 tok/s
    Usableqwen3:32b
  • Llama 3.3 70BClose to the big cloud models
    ~10 tok/s
    Usablellama3.3:70b
  • gpt-oss 120BOpenAI's largest open model
    ~97 tok/s
    Runs greatgpt-oss:120b
  • Qwen3 235B-A22BAlibaba's flagship open model, for multi-GPU rigs
    ~21 tok/s
    Usableqwen3:235b
  • DeepSeek R1 671BThe full DeepSeek R1, for the biggest rigs
    needs 406 GB
    Too bigdeepseek-r1:671b
Common questions

Can the Apple M2 Ultra run it?

Can the Apple M2 Ultra run gpt-oss 120B?

Yes, with 128 GB or more. gpt-oss 120B needs about 67 GB and the Apple M2 Ultra with 128 GB of unified memory leaves about 96 GB for models. Expect about 97 tok/s, faster than you can read. The 64 GB version doesn't have room.

Can the Apple M2 Ultra run Qwen3 235B-A22B?

Yes, with 192 GB or more. Qwen3 235B-A22B needs about 144 GB and the Apple M2 Ultra with 192 GB of unified memory leaves about 144 GB for models. Expect about 21 tok/s, about reading speed. The 64 and 128 GB versions don't have room.

Can the Apple M2 Ultra run DeepSeek R1 671B?

No. DeepSeek R1 671B needs about 406 GB and the Apple M2 Ultra has at most 192 GB of unified memory, of which about 144 GB is usable for models. The most capable model it runs well is Qwen3 235B-A22B, at about 21 tok/s.

How we estimate

Generating a token reads the model's active weights from memory once, so speed is roughly memory bandwidth (800 GB/s) divided by the active weight size, with efficiency calibrated on our own rack. Sizes are Ollama's default 4-bit downloads plus about 1.2 GB for context. macOS lets the GPU use about two thirds to three quarters of unified memory, so that is what we count. Real results are usually within about a third. Measured one yourself? Send us the number.

Want something bigger?

The Ryzen AI Max+ 395 mini PC, 128 GB runs gpt-oss 120B at about 31 tok/s, from $3,400 used.

See the builds

Compare

Similar cards

Every GPU we track

Head to head

The Apple M2 Ultra against its rivals

Every comparison