Will it run? / DeepSeek-R1 70B / Mac mini M2 (16GB)

Can the Mac mini M2 (16GB) run DeepSeek-R1 70B?

Won't fit No. DeepSeek-R1 70B needs about 44.5 GB of memory, and the Mac mini M2 (16GB) can give a model about 10.7 GB. You'd need a machine with more memory, or a smaller model.

–estimated tokens/sec
44.5 GBmemory needed
10.7 GBavailable to the model
100 GB/smemory bandwidth

Check the Mac mini M2 (16GB) price →

How we got this number

Each generated token reads the whole model from memory once: 43 GB. The Mac mini M2 (16GB) moves 100 GB/s, so the ceiling is 2.3 tokens/sec. Real machines reach a fraction of that ceiling; we use 80%, calibrated against a measured Mac run. Send us your real numbers and we'll replace the estimate.

Faster machines for DeepSeek-R1 70B

Mac Studio M5 Ultra (96GB)23 tok/s$5,499Check price →
Mac Studio M5 Ultra (256GB)23 tok/s$9,499Check price →
Mac Studio M5 Max (40-core GPU, 64GB)11 tok/s$3,799Check price →
Mac mini M5 Pro (64GB)5.7 tok/sCheck price →

Other models on the Mac mini M2 (16GB)

DeepSeek Coder v2 16BUsable, but slow9.0 tok/s
DeepSeek-R1 14BUsable, but slow8.9 tok/s
Qwen2.5 14BUsable, but slow8.9 tok/s
Qwen2.5 Coder 14BUsable, but slow8.9 tok/s
Phi 4 14BUsable, but slow8.8 tok/s
Qwen 3 14BUsable, but slow5.2 tok/s