llamaperf

Intel Arc A770 16GB vs M5 16GB for local LLMs

4 reports on the Intel Arc A770 16GB and 2 on the M5 16GB

Which is faster for local LLMs?

On Qwen3.8 27B at 3-bit, the Intel Arc A770 16GB runs at 12.0 tokens per second (one run) and the M5 16GB at 9.0 (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 3.6x higher on the Intel Arc A770 16GB (560 GB/s on the Intel Arc A770 16GB, 154 on the M5 16GB).

Intel Arc A770 16GB
Memory
16GB
Memory bandwidth
560 GB/s
FP16 compute
39.3 TFLOPS
Reports
4
M5 16GB
Memory
16GB unified
Memory bandwidth
154 GB/s
FP16 compute
not on record
Reports
2

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 A770 16GBM5 16GB
Qwen3.8 27B3-bit12.0one run9.0one 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.

ModelIntel Arc A770 16GBM5 16GB
Qwen3.8 27B36.5 t/sQ2_Kdoesn't fit at these settings
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 active120.8 t/sQ2_Kdoesn't fit at these settings
Qwen3.6 27B36.5 t/sQ2_Kdoesn't fit at these settings
Gemma 4 26B · 4B active81.4 t/sQ3_K_Sdoesn't fit at these settings
DeepSeek V4.1 Flash 552B · 16B activedoesn't fit at these settingsdoesn't fit at these settings

Change the context, RAM or model in the calculator: Intel Arc A770 16GB · M5 16GB

Every report on each card, with its source: Intel Arc A770 16GB · M5 16GB

More comparisons