llamaperf

M3 Ultra 192GB vs M3 Ultra 256GB

For running local LLMs · 3 reports across 3 models

Side A
M3 Ultra 192GB
Vendor
apple
VRAM
192GB
Memory
Unified
Side B
M3 Ultra 256GB
Vendor
apple
VRAM
256GB
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 →

ModelM3 Ultra 192GBM3 Ultra 256GB
DeepSeek V4 Flashup to 285B43.0n=1
GLM-5.3up to 321B37.4n=1
Minimax M317.3n=1

More comparisons