llamaperf

M4 24GB vs M5 Pro 24GB for local LLMs

8 reports on the M4 24GB and 6 on the M5 Pro 24GB

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 2.6x higher on the M5 Pro 24GB (120 GB/s on the M4 24GB, 307 on the M5 Pro 24GB). The estimates below compare them on the models people run most.

M4 24GB
Memory
24GB unified
Memory bandwidth
120 GB/s
FP16 compute
4.3 TFLOPS
Reports
8
M5 Pro 24GB
Memory
24GB unified
Memory bandwidth
307 GB/s
FP16 compute
not on record
Reports
6

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.

ModelM4 24GBM5 Pro 24GB
Qwen3.8 27B10.8 t/sQ2_K31.1 t/sQ2_K
Qwen3.8 125B · 6B activedoesn't fit at these settingsdoesn't fit at these settings
Qwen3.6 35B · 3B active35.8 t/sQ2_K102.9 t/sQ2_K
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 27B10.8 t/sQ2_K31.1 t/sQ2_K

Change the context, RAM or model in the calculator: M4 24GB · M5 Pro 24GB

Every report on each card, with its source: M4 24GB · M5 Pro 24GB

More comparisons