llamaperf

M2 Max 96GB vs RTX PRO 6000 Max-Q

For running local LLMs · 11 reports across 5 models

Side A
M2 Max 96GB
Vendor
apple
VRAM
96GB
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 →

ModelM2 Max 96GBRTX PRO 6000 Max-Q
Qwen3.8up to 2400B22.0n=2240.0n=2
Qwen3.6up to 35B28.0n=3
DeepSeek V4 Pro7.1n=2
DeepSeek V4 Flashup to 285B44.0n=1
Qwen3up to 235B43.0n=1

More comparisons