// RUN โ€” FITS

Can the Intel Arc Pro B70 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 B70

QuantFits?Max contextSpeedBeyond context
FP16 yes 424k 2217.9-2753.2 t/s ~145.9-181.1 (slow)
Q8 yes 425k 4435.7-5506.4 t/s ~291.8-362.3 (slow)
Q4 yes 426k 7920.9-9832.9 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 B70 run Routing Transformer (WT-103)?โ–ถ

Yes. At Q4 it generates ~7920.9-9832.9 tok/s and fits up to 426k 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 426k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.