llamaperf

M3 Max 36GB vs RTX 5060 Ti 16GB

For running local LLMs · 3 reports across 2 models

Side A
M3 Max 36GB
Vendor
apple
VRAM
36GB
Memory
Unified
Side B
RTX 5060 Ti 16GB
Vendor
nvidia
VRAM
16GB
Memory
Discrete

Tokens per second by model

ModelM3 Max 36GBRTX 5060 Ti 16GB
Gemma 4up to 31B16.0n=145.0n=1
Qwen3.6up to 35B22.0n=1

More comparisons