llamaperf

M4 32GB vs M4 Max 36GB

For running local LLMs · 2 reports across 1 model

Side A
M4 32GB
Vendor
apple
VRAM
32GB
Memory
Unified
Side B
M4 Max 36GB
Vendor
apple
VRAM
36GB
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 →

ModelM4 32GBM4 Max 36GB
Qwen3.8up to 2400B22.0n=2

More comparisons