llamaperf

M2 Max 96GB vs AMD RX 9070 XT 16GB for local LLMs

7 reports on the M2 Max 96GB and 12 on the AMD RX 9070 XT 16GB

Which is faster for local LLMs?

On Qwen3 8B at 4-bit, the M2 Max 96GB runs at 43.0 tokens per second (one run) and the AMD RX 9070 XT 16GB at 98.8 (one run). Those are community reports whose engines and settings differ, so the gap is a rough sign, not a controlled measure of the two cards. Memory bandwidth, which caps how fast a card can write, is 1.6x higher on the AMD RX 9070 XT 16GB (410 GB/s on the M2 Max 96GB, 640 on the AMD RX 9070 XT 16GB).

M2 Max 96GB
Memory
96GB unified
Memory bandwidth
410 GB/s
FP16 compute
13.6 TFLOPS
Reports
7
AMD RX 9070 XT 16GB
Memory
16GB
Memory bandwidth
640 GB/s
FP16 compute
195 TFLOPS
Reports
12

Measured on both

Median tokens per second from plain runs (one device, one request, no speculative decoding, the whole model in the device's memory) of the same model size at the same quant level. Engines and context lengths can still differ between the runs. How to read these

ModelM2 Max 96GBAMD RX 9070 XT 16GB
Qwen3 8B4-bit43.0one run98.8one run

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. Where a model was also measured above, the measurement wins.

ModelM2 Max 96GBAMD RX 9070 XT 16GB
Qwen3 8B17.6 t/sFP1654.2 t/sQ6_K
Qwen3.8 27B5.2 t/sFP1641.7 t/sQ2_K
Qwen3.8 125B · 6B active36.2 t/sQ3_K_Mdoesn't fit at these settings
Qwen3.6 35B · 3B active37.6 t/sQ8_0138.0 t/sQ2_K
DeepSeek V4 Flash 284B · 13B activedoesn't fit at these settingsdoesn't fit at these settings
Qwen3.6 27B5.2 t/sFP1641.7 t/sQ2_K
Gemma 4 26B · 4B active12.5 t/sFP1693.0 t/sQ3_K_S

Change the context, RAM or model in the calculator: M2 Max 96GB · AMD RX 9070 XT 16GB

Every report on each card, with its source: M2 Max 96GB · AMD RX 9070 XT 16GB

More comparisons