// RUN โ€” FITS

Can the Intel Arc A770 16GB run code2seq?

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

code2seq on the Intel Arc A770 16GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 201k 4389.2-5448.6 t/s ~313.5-389.2 (slow)
Q8 yes 201k 8778.4-10897.3 t/s ~627-778.4 (slow)
Q4 yes 201k 15675.7-19459.5 t/s ~1119.7-1390 (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 code2seq?โ–ถ

Yes. At Q4 it generates ~15675.7-19459.5 tok/s and fits up to 201k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~1119.7-1390 tok/s.

How much context fits?โ–ถ

At Q4, up to about 201k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.