llamaperf

M5 Pro 48GB vs M6 32GB for local LLMs

14 reports on the M5 Pro 48GB and 22 on the M6 32GB

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 1.8x higher on the M5 Pro 48GB (307 GB/s on the M5 Pro 48GB, 171 on the M6 32GB). The estimates below compare them on the models people run most.

M5 Pro 48GB
Memory
48GB unified
Memory bandwidth
307 GB/s
FP16 compute
not on record
Reports
14
M6 32GB
Memory
32GB unified
Memory bandwidth
171 GB/s
FP16 compute
not on record
Reports
22

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.

ModelM5 Pro 48GBM6 32GB
Qwen3.8 27B12.0 t/sQ6_K10.5 t/sQ4_K_S
Qwen3.8 125B · 6B activedoesn't fit at these settingsdoesn't fit at these settings
Qwen3.6 35B · 3B active47.5 t/sQ5_K_M38.2 t/sQ3_K_M
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 27B12.0 t/sQ6_K10.5 t/sQ4_K_S

Change the context, RAM or model in the calculator: M5 Pro 48GB · M6 32GB

Every report on each card, with its source: M5 Pro 48GB · M6 32GB

More comparisons