// RUN โ€” FITS

Can the Intel Arc A770 16GB run phi-3.5-mini?

Yes โ€” here's how fast and up to what context, with real measured numbers.

phi-3.5-mini on the Intel Arc A770 16GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 86k 42.7-53.1 t/s ~3.1-3.8 (slow)
Q8 yes 144k 85.5-106.1 t/s ~6.1-7.6 (slow)
Q4 yes 169k 152.6-189.5 t/s ~10.9-13.5 (slow)

Estimate (memory-bound). Beyond "max context" the KV cache spills to system RAM offload (depends on your system RAM) and speed drops to the "beyond" figure.

FAQ

Can the Intel Arc A770 16GB run phi-3.5-mini?โ–ถ

Yes. At Q4 it generates ~152.6-189.5 tok/s and fits up to 169k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~10.9-13.5 tok/s.

How much context fits?โ–ถ

At Q4, up to about 169k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.