// RUN โ€” FITS

Can the Intel Arc A770 16GB run IDEFICS-9B?

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

IDEFICS-9B on the Intel Arc A770 16GB

QuantFits?Max contextSpeedBeyond context
FP16 no โ€” โ€” โ€”
Q8 yes 32k 36.1-44.8 t/s ~2.6-3.2 (slow)
Q4 yes 62k 64.4-80 t/s ~4.6-5.7 (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 IDEFICS-9B?โ–ถ

Yes. At Q4 it generates ~64.4-80 tok/s and fits up to 62k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~4.6-5.7 tok/s.

How much context fits?โ–ถ

At Q4, up to about 62k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.