// RUN โ€” FITS

Can the Intel Arc Pro B70 run CARP?

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

CARP on the Intel Arc Pro B70

QuantFits?Max contextSpeedBeyond context
FP16 yes 407k 274.2-340.4 t/s ~18-22.4 (slow)
Q8 yes 417k 548.4-680.8 t/s ~36.1-44.8 (slow)
Q4 yes 421k 979.3-1215.7 t/s ~64.4-80 (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 B70 run CARP?โ–ถ

Yes. At Q4 it generates ~979.3-1215.7 tok/s and fits up to 421k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~64.4-80 tok/s.

How much context fits?โ–ถ

At Q4, up to about 421k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.