← Every GPUApple · 16 or 8 or 24 GB unified memory · 100 GB/s

What can the Apple M3 run?

With 16 GB, 4 of 12 popular open models fit. The best pick is Qwen3 4B at about 22 tok/s, about reading speed.

ollama run qwen3:4b

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

8 GB unified memory · about 5 GB for models

Every model the Apple M3 8 GB can run

1 of 12 fit. Best pick: Qwen3 4B.

  • Qwen3 4BQuick everyday chat and summaries
    ~22 tok/s
    Usableqwen3:4b
  • Qwen3 8BA solid all-rounder for chat and writing
    needs 7 GB
    Too bigqwen3:8b
  • Gemma 3 12BReads images as well as text
    needs 10 GB
    Too biggemma3:12b
  • Qwen3 14BNoticeably smarter at reasoning and code
    needs 11 GB
    Too bigqwen3:14b
  • gpt-oss 20BOpenAI's open model. Fast, strong reasoning
    needs 16 GB
    Too biggpt-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
16 GB unified memory · about 11 GB for models

Every model the Apple M3 16 GB can run

4 of 12 fit. Best pick: Qwen3 4B.

  • Qwen3 4BQuick everyday chat and summaries
    ~22 tok/s
    Usableqwen3:4b
  • Qwen3 8BA solid all-rounder for chat and writing
    ~11 tok/s
    Usableqwen3:8b
  • Gemma 3 12BReads images as well as text
    ~7 tok/s
    Slowgemma3:12b
  • Qwen3 14BNoticeably smarter at reasoning and code
    ~6 tok/s
    Slowqwen3:14b
  • gpt-oss 20BOpenAI's open model. Fast, strong reasoning
    needs 16 GB
    Too biggpt-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
24 GB unified memory · about 16 GB for models

Every model the Apple M3 24 GB can run

5 of 12 fit. Best pick: Qwen3 4B.

  • Qwen3 4BQuick everyday chat and summaries
    ~22 tok/s
    Usableqwen3:4b
  • Qwen3 8BA solid all-rounder for chat and writing
    ~11 tok/s
    Usableqwen3:8b
  • Gemma 3 12BReads images as well as text
    ~7 tok/s
    Slowgemma3:12b
  • Qwen3 14BNoticeably smarter at reasoning and code
    ~6 tok/s
    Slowqwen3:14b
  • gpt-oss 20BOpenAI's open model. Fast, strong reasoning
    ~18 tok/s
    Usablegpt-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
Common questions

Can the Apple M3 run it?

Can the Apple M3 run Qwen3 14B?

Yes, with 16 GB or more. Qwen3 14B needs about 11 GB and the Apple M3 with 16 GB of unified memory leaves about 11 GB for models. Expect about 6 tok/s, slow, but it works. The 8 GB version doesn't have room.

Can the Apple M3 run gpt-oss 20B?

Yes, with 24 GB or more. gpt-oss 20B needs about 16 GB and the Apple M3 with 24 GB of unified memory leaves about 16 GB for models. Expect about 18 tok/s, about reading speed. The 8 and 16 GB versions don't have room.

Can the Apple M3 run Gemma 3 27B?

No. Gemma 3 27B needs about 19 GB and the Apple M3 has at most 24 GB of unified memory, of which about 16 GB is usable for models. The most capable model it runs well is Qwen3 4B, at about 22 tok/s.

How we estimate

Generating a token reads the model's active weights from memory once, so speed is roughly memory bandwidth (100 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 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 M3 against its rivals

Every comparison