// RUN โ€” FITS

Can the NVIDIA B200 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 NVIDIA B200

QuantFits?Max contextSpeedBeyond context
FP16 yes 2670k 36729.6-43773.6 t/s ~183.6-218.9 (slow)
Q8 yes 2671k 73459.1-87547.2 t/s ~367.3-437.7 (slow)
Q4 yes 2672k 131177-156334.2 t/s ~655.9-781.7 (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 NVIDIA B200 run Routing Transformer (WT-103)?โ–ถ

Yes. At Q4 it generates ~131177-156334.2 tok/s and fits up to 2672k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~655.9-781.7 tok/s.

How much context fits?โ–ถ

At Q4, up to about 2672k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.