llamaperf

M5 Pro 64GB vs RTX 5060 Ti 16GB

For running local LLMs · 33 reports across 7 models

Side A
M5 Pro 64GB
Vendor
apple
VRAM
64GB
Memory
Unified
Side B
RTX 5060 Ti 16GB
Vendor
nvidia
VRAM
16GB
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 5060 Ti 16GB
Qwen3.8up to 2400B27.6n=276.7n=17
Qwen3.6up to 35B52.2n=6
DeepSeek V4 Flashup to 285B15.0n=311.0n=1
Gemma 4up to 31B73.9n=1
Museup to 30B18.0n=1
Ornith1.5up to 35B105.0n=1
Qwen3up to 235B52.0n=1

More comparisons