// RUN โ€” FITS

Can the Intel Arc A770 16GB run Reason-ModernColBERT?

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

Reason-ModernColBERT on the Intel Arc A770 16GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 197k 1082.7-1344 t/s ~77.3-96 (slow)
Q8 yes 199k 2165.3-2688 t/s ~154.7-192 (slow)
Q4 yes 200k 3866.7-4800 t/s ~276.2-342.9 (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 Reason-ModernColBERT?โ–ถ

Yes. At Q4 it generates ~3866.7-4800 tok/s and fits up to 200k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~276.2-342.9 tok/s.

How much context fits?โ–ถ

At Q4, up to about 200k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.