M2 Max 96GB vs RTX 4090

For running local LLMs · 5 reports across 2 models

Side A

Vendor: apple
VRAM: 96GB
Memory: Unified

Side B

Vendor: nvidia
VRAM: 24GB
Memory: Discrete

Tokens per second by model

Model	M2 Max 96GB	RTX 4090
Qwen3.6up to 35B	28.0n=2	25.0n=1
Gemma 4up to 31B	—	149.6n=2

More comparisons