// RUN โ€” FITS

Can the Intel Arc B580 12GB run SANA 1.5 4.8B?

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

SANA 1.5 4.8B on the Intel Arc B580 12GB

QuantFits?Max contextSpeedBeyond context
FP16 no โ€” โ€” โ€”
Q8 yes 72k 55.1-68.4 t/s ~4.8-6 (slow)
Q4 yes 105k 98.4-122.1 t/s ~8.6-10.7 (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 B580 12GB run SANA 1.5 4.8B?โ–ถ

Yes. At Q4 it generates ~98.4-122.1 tok/s and fits up to 105k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~8.6-10.7 tok/s.

How much context fits?โ–ถ

At Q4, up to about 105k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.