llamaperf

Intel Arc Pro B70 vs M3 Pro 18GB for local LLMs

14 reports on the Intel Arc Pro B70 and 1 on the M3 Pro 18GB

Which is faster for local LLMs?

On Qwen3 8B at 4-bit, the Intel Arc Pro B70 runs at 77.7 tokens per second (one run) and the M3 Pro 18GB at 25.2 (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 4.0x higher on the Intel Arc Pro B70 (608 GB/s on the Intel Arc Pro B70, 154 on the M3 Pro 18GB).

Intel Arc Pro B70
Memory
32GB
Memory bandwidth
608 GB/s
FP16 compute
183.5 TFLOPS
Reports
14
M3 Pro 18GB
Memory
18GB unified
Memory bandwidth
154 GB/s
FP16 compute
7.4 TFLOPS
Reports
1

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

ModelIntel Arc Pro B70M3 Pro 18GB
Qwen3 8B4-bit77.7one run25.2one 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.

ModelIntel Arc Pro B70M3 Pro 18GB
Qwen3 8B20.9 t/sFP1633.8 t/sQ3_K_M
Qwen3.8 27B15.2 t/sQ6_Kdoesn't fit at these settings
Qwen3.8 125B · 6B active18.6 t/sQ2_K, experts in RAMdoesn'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 active55.3 t/sQ5_K_Mdoesn't fit at these settings
Qwen3.6 27B15.2 t/sQ6_Kdoesn't fit at these settings
Gemma 4 26B · 4B active38.8 t/sQ6_K35.1 t/sQ2_K

Change the context, RAM or model in the calculator: Intel Arc Pro B70 · M3 Pro 18GB

Every report on each card, with its source: Intel Arc Pro B70 · M3 Pro 18GB

More comparisons