// RUN โ€” FITS

Can the Intel Arc B580 12GB run Minerva 3B?

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

Minerva 3B on the Intel Arc B580 12GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 54k 44.1-54.7 t/s ~3.9-4.8 (slow)
Q8 yes 100k 88.2-109.4 t/s ~7.7-9.6 (slow)
Q4 yes 120k 157.4-195.4 t/s ~13.8-17.1 (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 Minerva 3B?โ–ถ

Yes. At Q4 it generates ~157.4-195.4 tok/s and fits up to 120k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~13.8-17.1 tok/s.

How much context fits?โ–ถ

At Q4, up to about 120k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.