// RUN โ€” FITS

Can the Intel Arc Pro B60 run Routing Transformer (WT-103)?

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

Routing Transformer (WT-103) on the Intel Arc Pro B60

QuantFits?Max contextSpeedBeyond context
FP16 yes 312k 1663.4-2064.9 t/s ~145.9-181.1 (slow)
Q8 yes 313k 3326.8-4129.8 t/s ~291.8-362.3 (slow)
Q4 yes 313k 5940.7-7374.7 t/s ~521.1-646.9 (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 Routing Transformer (WT-103)?โ–ถ

Yes. At Q4 it generates ~5940.7-7374.7 tok/s and fits up to 313k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~521.1-646.9 tok/s.

How much context fits?โ–ถ

At Q4, up to about 313k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.