llamaperf

M2 Max 64GB vs M5 Ultra 96GB for local LLMs

20 reports on the M2 Max 64GB and 12 on the M5 Ultra 96GB

Which is faster for local LLMs?

Nobody has reported the same model at the same quant on both cards yet, so there's no measured head-to-head. Memory bandwidth, which caps how fast a card can write, is 3.0x higher on the M5 Ultra 96GB (410 GB/s on the M2 Max 64GB, 1,229 on the M5 Ultra 96GB). The estimates below compare them on the models people run most.

M2 Max 64GB
Memory
64GB unified
Memory bandwidth
410 GB/s
FP16 compute
13.6 TFLOPS
Reports
20
M5 Ultra 96GB
Memory
96GB unified
Memory bandwidth
1,229 GB/s
FP16 compute
not on record
Reports
12

Estimated by the calculator

The quant the calculator recommends for each card and its estimated speed at a 32,768-token context with 32 GB of system RAM, from memory bandwidth and the model's shape.

ModelM2 Max 64GBM5 Ultra 96GB
Qwen3.8 27B10.4 t/sQ8_014.9 t/sFP16
Qwen3.8 125B · 6B active47.5 t/sQ2_K103.1 t/sQ3_K_M
Qwen3.6 35B · 3B active32.9 t/sQ8_0107.0 t/sQ8_0
DeepSeek V4 Flash 284B · 13B activedoesn't fit at these settingsdoesn't fit at these settings
DeepSeek V4.1 Flash 552B · 16B activedoesn't fit at these settingsdoesn't fit at these settings
Qwen3.6 27B10.4 t/sQ8_014.9 t/sFP16

Change the context, RAM or model in the calculator: M2 Max 64GB · M5 Ultra 96GB

Every report on each card, with its source: M2 Max 64GB · M5 Ultra 96GB

More comparisons