What can the Apple M2 Pro run?
With 16 GB, 4 of 12 popular open models fit. The best pick is Qwen3 8B at about 21 tok/s, about reading speed.
ollama run qwen3:8bFirst time? Install Ollama, then paste that into a terminal. Is this your machine? Check it on the homepage.
Every model the Apple M2 Pro 16 GB can run
4 of 12 fit. Best pick: Qwen3 8B.
- Qwen3 4BQuick everyday chat and summaries~44 tok/sRuns great
qwen3:4b - Qwen3 8BA solid all-rounder for chat and writing~21 tok/sUsable
qwen3:8b - Gemma 3 12BReads images as well as text~14 tok/sUsable
gemma3:12b - Qwen3 14BNoticeably smarter at reasoning and code~12 tok/sUsable
qwen3:14b - gpt-oss 20BOpenAI's open model. Fast, strong reasoningneeds 16 GBToo big
gpt-oss:20b - Gemma 3 27BGoogle's best open model for its sizeneeds 19 GBToo big
gemma3:27b - Qwen3 30B-A3B30B smarts at small-model speedneeds 21 GBToo big
qwen3:30b - Qwen3 32BStrong coding and long answersneeds 22 GBToo big
qwen3:32b - Llama 3.3 70BClose to the big cloud modelsneeds 45 GBToo big
llama3.3:70b - gpt-oss 120BOpenAI's largest open modelneeds 67 GBToo big
gpt-oss:120b - Qwen3 235B-A22BAlibaba's flagship open model, for multi-GPU rigsneeds 144 GBToo big
qwen3:235b - DeepSeek R1 671BThe full DeepSeek R1, for the biggest rigsneeds 406 GBToo big
deepseek-r1:671b
Every model the Apple M2 Pro 32 GB can run
8 of 12 fit. Best pick: Qwen3 30B-A3B.
- Qwen3 4BQuick everyday chat and summaries~44 tok/sRuns great
qwen3:4b - Qwen3 8BA solid all-rounder for chat and writing~21 tok/sUsable
qwen3:8b - Gemma 3 12BReads images as well as text~14 tok/sUsable
gemma3:12b - Qwen3 14BNoticeably smarter at reasoning and code~12 tok/sUsable
qwen3:14b - gpt-oss 20BOpenAI's open model. Fast, strong reasoning~35 tok/sRuns great
gpt-oss:20b - Gemma 3 27BGoogle's best open model for its size~6 tok/sSlow
gemma3:27b - Qwen3 30B-A3B30B smarts at small-model speed~35 tok/sRuns great
qwen3:30b - Qwen3 32BStrong coding and long answers~6 tok/sSlow
qwen3:32b - Llama 3.3 70BClose to the big cloud modelsneeds 45 GBToo big
llama3.3:70b - gpt-oss 120BOpenAI's largest open modelneeds 67 GBToo big
gpt-oss:120b - Qwen3 235B-A22BAlibaba's flagship open model, for multi-GPU rigsneeds 144 GBToo big
qwen3:235b - DeepSeek R1 671BThe full DeepSeek R1, for the biggest rigsneeds 406 GBToo big
deepseek-r1:671b
Can the Apple M2 Pro run it?
Can the Apple M2 Pro run Qwen3 30B-A3B?
Yes, with 32 GB or more. Qwen3 30B-A3B needs about 21 GB and the Apple M2 Pro with 32 GB of unified memory leaves about 21 GB for models. Expect about 35 tok/s, faster than you can read. The 16 GB version doesn't have room.
Can the Apple M2 Pro run Qwen3 32B?
Yes, with 32 GB or more. Qwen3 32B needs about 22 GB and the Apple M2 Pro with 32 GB of unified memory leaves about 21 GB for models. Expect about 6 tok/s, slow, but it works. The 16 GB version doesn't have room.
Can the Apple M2 Pro run Llama 3.3 70B?
No. Llama 3.3 70B needs about 45 GB and the Apple M2 Pro has at most 32 GB of unified memory, of which about 21 GB is usable for models. The most capable model it runs well is Qwen3 30B-A3B, at about 35 tok/s.
Real runs on the Apple M2 Pro
Loading measured runs…
Generating a token reads the model's active weights from memory once, so speed is roughly memory bandwidth (200 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.
The Used workstation + 2× Tesla P100 runs Qwen3 32B at about 20 tok/s, from $750 used.