llamaperf

CMP 170HX vs M2 Max 96GB

For running local LLMs · 10 reports across 4 models

Side A
CMP 170HX
Vendor
nvidia
VRAM
8GB
Memory
Discrete
Side B
M2 Max 96GB
Vendor
apple
VRAM
96GB
Memory
Unified

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 →

ModelCMP 170HXM2 Max 96GB
Qwen3.6up to 35B210.0n=228.0n=3
Qwen3.8up to 2400Bn=122.0n=2
DeepSeek V4 Flashup to 285B29.0n=1
Qwen3up to 235B43.0n=1

More comparisons