// RUN โ€” FITS

Can the Intel Arc A770 16GB run MiniCPM-2.4B?

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

MiniCPM-2.4B on the Intel Arc A770 16GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 127k 66.5-82.6 t/s ~4.8-5.9 (slow)
Q8 yes 164k 133-165.1 t/s ~9.5-11.8 (slow)
Q4 yes 181k 237.5-294.8 t/s ~17-21.1 (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 MiniCPM-2.4B?โ–ถ

Yes. At Q4 it generates ~237.5-294.8 tok/s and fits up to 181k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~17-21.1 tok/s.

How much context fits?โ–ถ

At Q4, up to about 181k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.