// RUN โ€” FITS

Can the Intel Arc B580 12GB run SeqVec?

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

SeqVec on the Intel Arc B580 12GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 143k 1421.9-1765.2 t/s ~124.7-154.8 (slow)
Q8 yes 144k 2843.9-3530.3 t/s ~249.5-309.7 (slow)
Q4 yes 145k 5078.3-6304.1 t/s ~445.5-553 (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 B580 12GB run SeqVec?โ–ถ

Yes. At Q4 it generates ~5078.3-6304.1 tok/s and fits up to 145k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~445.5-553 tok/s.

How much context fits?โ–ถ

At Q4, up to about 145k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.