M2 8GB vs M5 Max 64GB

For running local LLMs · 2 reports across 2 models

Side A

Vendor: apple
VRAM: 8GB
Memory: Unified

Side B

Vendor: apple
VRAM: 64GB
Memory: Unified

Tokens per second by model

Model	M2 8GB	M5 Max 64GB
Gemma 4up to 31B	16.0n=1	—
Qwen3.6up to 35B	—	32.0n=1

More comparisons