llamaperf

M5 Pro 64GB vs RTX PRO 6000 Max-Q

For running local LLMs · 10 reports across 3 models

Side A
M5 Pro 64GB
Vendor
apple
VRAM
64GB
Memory
Unified
Side B
RTX PRO 6000 Max-Q
Vendor
nvidia
VRAM
96GB
Memory
Discrete

Highest reported generation speed by model family

These maxima come from different community setups. Model size, quantization, GPU count, offloading and concurrency may differ. They do not establish which GPU is faster for the same workload. Check the comparison conditions →

ModelM5 Pro 64GBRTX PRO 6000 Max-Q
DeepSeek V4 Flashup to 285B15.0n=344.0n=1
Qwen3.8up to 2400B27.6n=2240.0n=2
DeepSeek V4 Pro7.1n=2

More comparisons