Calculator SubmitSign in

M3 Max 36GB vs RTX 5090

For running local LLMs · 10 reports across 2 models

Side A

Vendor: apple
VRAM: 36GB
Memory: Unified

Side B

Vendor: nvidia
VRAM: 32GB
Memory: Discrete

Tokens per second by model

Model	M3 Max 36GB	RTX 5090
Qwen3.6up to 35B	—	3238.0n=7
Gemma 4up to 31B	—	578.0n=3

More comparisons