Will it run? / Gemma 2 27B / Mac Studio M5 Max (40-core GPU, 64GB)

Can the Mac Studio M5 Max (40-core GPU, 64GB) run Gemma 2 27B?

Fast Yes, at about 31 tokens/sec (estimated). Replies stream faster than you can read.

31estimated tokens/sec
17.5 GBmemory needed
48 GBavailable to the model
614 GB/smemory bandwidth
ollama run gemma2:27b

Check the Mac Studio M5 Max (40-core GPU, 64GB) price →

How we got this number

Each generated token reads the whole model from memory once: 16 GB. The Mac Studio M5 Max (40-core GPU, 64GB) moves 614 GB/s, so the ceiling is 38 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 Gemma 2 27B

Mac Studio M5 Ultra (96GB)61 tok/s$5,499Check price →
Mac Studio M5 Ultra (256GB)61 tok/s$9,499Check price →
Mac mini M5 Pro (64GB)15 tok/sCheck price →
NVIDIA DGX Spark (128GB)12 tok/sCheck price →

Other models on the Mac Studio M5 Max (40-core GPU, 64GB)

lfm 2.5 8B (A1B)Fast120+ tok/s
Gemma 3 4BFast120+ tok/s
Qwen 3 30B (A3B)Fast120+ tok/s
Qwen3.5 4BFast120+ tok/s
Qwen3.5 35B (A3B)Fast120+ tok/s
Qwen3 Coder 30B (A3B)Fast120+ tok/s