llamaperf

M2 Max 96GB vs RTX 5060 Ti 16GB

For running local LLMs · 5 reports across 2 models

Side A
M2 Max 96GB
Vendor
apple
VRAM
96GB
Memory
Unified
Side B
RTX 5060 Ti 16GB
Vendor
nvidia
VRAM
16GB
Memory
Discrete

Tokens per second by model

ModelM2 Max 96GBRTX 5060 Ti 16GB
Qwen3.6up to 35B28.0n=222.0n=2
Gemma 4up to 31B45.0n=1

More comparisons