Which AI models can the Apple M2 Pro (32GB) run?

Every model we track, checked against the Apple M2 Pro (32GB) at 8K context.

ModelRuns?Best fit
Llama 3.2 1BYesFP16 · ~3.3 GB · ~48 tok/s
Llama 3.2 3BYesFP16 · ~8 GB · ~19 tok/s
Llama 3.1 8BYesFP16 · ~17.7 GB · ~7 tok/s
Llama 3.1 70BNoNeeds ~46.1 GB at Q4_K_M; 21.4 GB available
Qwen2.5 7BYesFP16 · ~16.3 GB · ~8 tok/s
Qwen2.5 14BYesQ8_0 · ~17.8 GB · ~8 tok/s
Qwen2.5 32BYes, with heavy quantizationQ3_K_M · ~18.8 GB · ~7 tok/s
Qwen2.5 72BNoNeeds ~47.4 GB at Q4_K_M; 21.4 GB available
Qwen3 8BYesFP16 · ~18.2 GB · ~7 tok/s
Qwen3 30B-A3BYesQ4_K_M · ~19.9 GB · ~60 tok/s
DeepSeek R1 Distill Qwen 32BYes, with heavy quantizationQ3_K_M · ~18.8 GB · ~7 tok/s
Mistral 7B v0.3YesFP16 · ~16.2 GB · ~8 tok/s
Mistral Nemo 12BYesQ8_0 · ~14.9 GB · ~9 tok/s
Mistral Small 24BYesQ6_K · ~21.3 GB · ~6 tok/s
Mixtral 8x7BYes, with heavy quantizationQ2_K · ~19.2 GB · ~25 tok/s
Gemma 2 9BYesQ8_0 · ~13.2 GB · ~12 tok/s
Gemma 2 27BYesQ4_K_M · ~20.2 GB · ~7 tok/s
Gemma 3 4BYesFP16 · ~10.3 GB · ~14 tok/s
Gemma 3 12BYesQ8_0 · ~16.8 GB · ~9 tok/s
Gemma 3 27BYesQ4_K_M · ~21.4 GB · ~7 tok/s
Phi-3.5 Mini 3.8BYesFP16 · ~11.5 GB · ~16 tok/s
Phi-4 14BYesQ8_0 · ~17.9 GB · ~8 tok/s
Qwen3 4BYesFP16 · ~9.8 GB · ~15 tok/s
Qwen3 14BYesQ8_0 · ~17.7 GB · ~8 tok/s
Qwen3 32BYes, with heavy quantizationQ3_K_M · ~18.8 GB · ~7 tok/s
Qwen3 Coder 30B-A3BYesQ4_K_M · ~19.9 GB · ~60 tok/s
gpt-oss 20BYesQ6_K · ~18.1 GB · ~41 tok/s
gpt-oss 120BNoNeeds ~72 GB at Q4_K_M; 21.4 GB available
Llama 4 Scout 17B-16ENoNeeds ~68.3 GB at Q4_K_M; 21.4 GB available
Run it in the cloud

Need more than 32 GB? Rent a bigger GPU by the hour.

Rent a cloud GPU by the hour. No upfront cost, cancel any time.