← Every GPUApple · 24 or 48 or 64 GB unified memory · 307 GB/s

What can the Apple M5 Pro run?

With 24 GB, 5 of 12 popular open models fit. The best pick is gpt-oss 20B at about 54 tok/s, faster than you can read.

ollama run gpt-oss:20b

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

24 GB unified memory · about 16 GB for models

Every model the Apple M5 Pro 24 GB can run

5 of 12 fit. Best pick: gpt-oss 20B.

  • Qwen3 4BQuick everyday chat and summaries
    ~68 tok/s
    Runs greatqwen3:4b
  • Qwen3 8BA solid all-rounder for chat and writing
    ~32 tok/s
    Runs greatqwen3:8b
  • Gemma 3 12BReads images as well as text
    ~21 tok/s
    Usablegemma3:12b
  • Qwen3 14BNoticeably smarter at reasoning and code
    ~18 tok/s
    Usableqwen3:14b
  • gpt-oss 20BOpenAI's open model. Fast, strong reasoning
    ~54 tok/s
    Runs greatgpt-oss:20b
  • Gemma 3 27BGoogle's best open model for its size
    needs 19 GB
    Too biggemma3:27b
  • Qwen3 30B-A3B30B smarts at small-model speed
    needs 21 GB
    Too bigqwen3:30b
  • Qwen3 32BStrong coding and long answers
    needs 22 GB
    Too bigqwen3:32b
  • Llama 3.3 70BClose to the big cloud models
    needs 45 GB
    Too bigllama3.3:70b
  • 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
48 GB unified memory · about 36 GB for models

Every model the Apple M5 Pro 48 GB can run

8 of 12 fit. Best pick: Qwen3 30B-A3B.

  • Qwen3 4BQuick everyday chat and summaries
    ~68 tok/s
    Runs greatqwen3:4b
  • Qwen3 8BA solid all-rounder for chat and writing
    ~32 tok/s
    Runs greatqwen3:8b
  • Gemma 3 12BReads images as well as text
    ~21 tok/s
    Usablegemma3:12b
  • Qwen3 14BNoticeably smarter at reasoning and code
    ~18 tok/s
    Usableqwen3:14b
  • gpt-oss 20BOpenAI's open model. Fast, strong reasoning
    ~54 tok/s
    Runs greatgpt-oss:20b
  • Gemma 3 27BGoogle's best open model for its size
    ~10 tok/s
    Slowgemma3:27b
  • Qwen3 30B-A3B30B smarts at small-model speed
    ~54 tok/s
    Runs greatqwen3:30b
  • Qwen3 32BStrong coding and long answers
    ~8 tok/s
    Slowqwen3:32b
  • Llama 3.3 70BClose to the big cloud models
    needs 45 GB
    Too bigllama3.3:70b
  • 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
64 GB unified memory · about 48 GB for models

Every model the Apple M5 Pro 64 GB can run

9 of 12 fit. Best pick: Qwen3 30B-A3B.

  • Qwen3 4BQuick everyday chat and summaries
    ~68 tok/s
    Runs greatqwen3:4b
  • Qwen3 8BA solid all-rounder for chat and writing
    ~32 tok/s
    Runs greatqwen3:8b
  • Gemma 3 12BReads images as well as text
    ~21 tok/s
    Usablegemma3:12b
  • Qwen3 14BNoticeably smarter at reasoning and code
    ~18 tok/s
    Usableqwen3:14b
  • gpt-oss 20BOpenAI's open model. Fast, strong reasoning
    ~54 tok/s
    Runs greatgpt-oss:20b
  • Gemma 3 27BGoogle's best open model for its size
    ~10 tok/s
    Slowgemma3:27b
  • Qwen3 30B-A3B30B smarts at small-model speed
    ~54 tok/s
    Runs greatqwen3:30b
  • Qwen3 32BStrong coding and long answers
    ~8 tok/s
    Slowqwen3:32b
  • Llama 3.3 70BClose to the big cloud models
    ~4 tok/s
    Slowllama3.3:70b
  • 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
Common questions

Can the Apple M5 Pro run it?

Can the Apple M5 Pro run Qwen3 32B?

Yes, with 48 GB or more. Qwen3 32B needs about 22 GB and the Apple M5 Pro with 48 GB of unified memory leaves about 36 GB for models. Expect about 8 tok/s, slow, but it works. The 24 GB version doesn't have room.

Can the Apple M5 Pro run Llama 3.3 70B?

Yes, with 64 GB or more. Llama 3.3 70B needs about 45 GB and the Apple M5 Pro with 64 GB of unified memory leaves about 48 GB for models. Expect about 4 tok/s, slow, but it works. The 24 and 48 GB versions don't have room.

Can the Apple M5 Pro run gpt-oss 120B?

No. gpt-oss 120B needs about 67 GB and the Apple M5 Pro has at most 64 GB of unified memory, of which about 48 GB is usable for models. The most capable model it runs well is Qwen3 30B-A3B, at about 54 tok/s.

Measured, not estimated

Real runs on the Apple M5 Pro

Loading measured runs…

How we estimate

Generating a token reads the model's active weights from memory once, so speed is roughly memory bandwidth (307 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 runs are on the leaderboard.

Want something bigger?

The Used workstation + 2× Tesla P100 runs Qwen3 32B at about 20 tok/s, from $750 used.

See the builds

Compare

Similar cards

Every GPU we track

Head to head

The Apple M5 Pro against its rivals

Every comparison