// RUN โ€” FITS

Can the Intel Arc Pro B60 run ESM1b?

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

ESM1b on the Intel Arc Pro B60

QuantFits?Max contextSpeedBeyond context
FP16 yes 294k 202.7-251.6 t/s ~17.8-22.1 (slow)
Q8 yes 304k 405.4-503.2 t/s ~35.6-44.1 (slow)
Q4 yes 308k 723.9-898.7 t/s ~63.5-78.8 (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 ESM1b?โ–ถ

Yes. At Q4 it generates ~723.9-898.7 tok/s and fits up to 308k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~63.5-78.8 tok/s.

How much context fits?โ–ถ

At Q4, up to about 308k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.