llamaperf

M4 Max 128GB vs M4 Pro 48GB

For running local LLMs · 10 reports across 5 models

Side A
M4 Max 128GB
Vendor
apple
VRAM
128GB
Memory
Unified
Side B
M4 Pro 48GB
Vendor
apple
VRAM
48GB
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 Max 128GBM4 Pro 48GB
Museup to 30B25.0n=118.0n=2
Qwen3.8up to 2400B15.2n=220.3n=1
GLM-5.3up to 321Bn=11.8n=1
LingBot-World-V2up to 1Bn=1
Qwen3.6up to 35B72.5n=1

More comparisons