llamaperf

M3 Pro 18GB vs AMD RX 6700 XT for local LLMs

1 report on the M3 Pro 18GB and 3 on the AMD RX 6700 XT

Which is faster for local LLMs?

On Qwen3 8B at 4-bit, the M3 Pro 18GB runs at 25.2 tokens per second (one run) and the AMD RX 6700 XT at 61.0 (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 2.5x higher on the AMD RX 6700 XT (154 GB/s on the M3 Pro 18GB, 384 on the AMD RX 6700 XT).

M3 Pro 18GB
Memory
18GB unified
Memory bandwidth
154 GB/s
FP16 compute
7.4 TFLOPS
Reports
1
AMD RX 6700 XT
Memory
12GB
Memory bandwidth
384 GB/s
FP16 compute
26.4 TFLOPS
Reports
3

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

ModelM3 Pro 18GBAMD RX 6700 XT
Qwen3 8B4-bit25.2one run61.0one 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.

ModelM3 Pro 18GBAMD RX 6700 XT
Qwen3 8B33.8 t/sQ3_K_M60.3 t/sQ3_K_M
Qwen3.8 27Bdoesn't fit at these settings1.6 t/sQ8_0, layers on CPU
Qwen3.8 125B · 6B activedoesn't fit at these settingsdoesn't fit at these settings
DeepSeek V4 Flash 284B · 13B activedoesn't fit at these settingsdoesn't fit at these settings
Qwen3.6 35B · 3B activedoesn't fit at these settings13.3 t/sQ6_K, experts in RAM
Qwen3.6 27Bdoesn't fit at these settings1.6 t/sQ8_0, layers on CPU
Gemma 4 26B · 4B active35.1 t/sQ2_K62.7 t/sQ2_K

Change the context, RAM or model in the calculator: M3 Pro 18GB · AMD RX 6700 XT

Every report on each card, with its source: M3 Pro 18GB · AMD RX 6700 XT

More comparisons