llamaperf

M1 Max 64GB vs M1 Ultra 128GB

For running local LLMs · 6 reports across 3 models

Side A
M1 Max 64GB
Vendor
apple
VRAM
64GB
Memory
Unified
Side B
M1 Ultra 128GB
Vendor
apple
VRAM
128GB
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 →

ModelM1 Max 64GBM1 Ultra 128GB
Qwen3.8up to 2400B21.0n=331.2n=1
DeepSeek V4up to 284B16.0n=1
DeepSeek V4 Flashup to 285B8.0n=1

More comparisons