llamaperf

M5 Max 128GB vs AMD RX 9070 XT 16GB for local LLMs

49 reports on the M5 Max 128GB and 21 on the AMD RX 9070 XT 16GB

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 about the same on both (614 GB/s on the M5 Max 128GB, 640 on the AMD RX 9070 XT 16GB). The estimates below compare them on the models people run most.

M5 Max 128GB
Memory
128GB unified
Memory bandwidth
614 GB/s
FP16 compute
not on record
Reports
49
AMD RX 9070 XT 16GB
Memory
16GB
Memory bandwidth
640 GB/s
FP16 compute
195 TFLOPS
Reports
21

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 Max 128GBAMD RX 9070 XT 16GB
Qwen3.8 27B9.0 t/sFP1641.7 t/sQ2_K
Qwen3.8 125B · 6B active41.2 t/sQ5_K_Sdoesn't fit at these settings
Qwen3.6 35B · 3B active28.5 t/sFP16138.0 t/sQ2_K
DeepSeek V4 Flash 284B · 13B active64.8 t/sQ2_Kdoesn't fit at these settings
Qwen3.6 27B9.0 t/sFP1641.7 t/sQ2_K
Gemma 4 26B · 4B active24.4 t/sFP1693.0 t/sQ3_K_S

Change the context, RAM or model in the calculator: M5 Max 128GB · AMD RX 9070 XT 16GB

Every report on each card, with its source: M5 Max 128GB · AMD RX 9070 XT 16GB

More comparisons