// RUN โ€” FITS

Can the Intel Arc Pro B60 run Novae?

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

Novae on the Intel Arc Pro B60

QuantFits?Max contextSpeedBeyond context
FP16 yes 313k 4132.5-5130 t/s ~362.5-450 (slow)
Q8 yes 314k 8265-10260 t/s ~725-900 (slow)
Q4 yes 314k 14758.9-18321.4 t/s ~1294.6-1607.1 (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 Pro B60 run Novae?โ–ถ

Yes. At Q4 it generates ~14758.9-18321.4 tok/s and fits up to 314k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~1294.6-1607.1 tok/s.

How much context fits?โ–ถ

At Q4, up to about 314k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.