// RUN โ€” FITS

Can the NVIDIA A100 SXM4 80GB 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 A100 SXM4 80GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 1098k 9361.4-11156.8 t/s ~183.6-218.9 (slow)
Q8 yes 1099k 18722.9-22313.6 t/s ~367.3-437.7 (slow)
Q4 yes 1099k 33433.7-39845.7 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 A100 SXM4 80GB run Routing Transformer (WT-103)?โ–ถ

Yes. At Q4 it generates ~33433.7-39845.7 tok/s and fits up to 1099k 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 1099k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.