Will it run? / Llama 3.2 Vision 90B / Mac Studio M5 Ultra (96GB)

Can the Mac Studio M5 Ultra (96GB) run Llama 3.2 Vision 90B?

Comfortable Yes, at about 18 tokens/sec (estimated). That reads at a comfortable pace.

18estimated tokens/sec
56.5 GBmemory needed
72 GBavailable to the model
1228.8 GB/smemory bandwidth
ollama run llama3.2-vision:90b

Check the Mac Studio M5 Ultra (96GB) price →

How we got this number

Each generated token reads the whole model from memory once: 55 GB. The Mac Studio M5 Ultra (96GB) moves 1228.8 GB/s, so the ceiling is 22 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 Llama 3.2 Vision 90B

Mac Studio M5 Ultra (256GB)18 tok/s$9,499Check price →
Mac Studio M5 Max (40-core GPU, 64GB)5.4 tok/s$3,799Check price →
NVIDIA DGX Spark (128GB)3.5 tok/sCheck price →
Ryzen AI Max+ 395 mini PC (128GB)3.3 tok/sCheck price →

Other models on the Mac Studio M5 Ultra (96GB)

Nemotron 3.5 lightning 30B (A3B)Fast120+ tok/s
Qwen 3 30B (A3B)Fast120+ tok/s
Gemma 4 26B (A4B)Fast120+ tok/s
Qwen3.5 35B (A3B)Fast120+ tok/s
gpt-oss 20BFast120+ tok/s
gpt-oss 120BFast120+ tok/s