// RUN โ€” FITS

Can the NVIDIA GeForce RTX 3080 Ti 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 GeForce RTX 3080 Ti

QuantFits?Max contextSpeedBeyond context
FP16 yes 143k 4187.2-4990.2 t/s ~183.6-218.9 (slow)
Q8 yes 144k 8374.3-9980.4 t/s ~367.3-437.7 (slow)
Q4 yes 145k 14954.2-17822.1 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 GeForce RTX 3080 Ti run Routing Transformer (WT-103)?โ–ถ

Yes. At Q4 it generates ~14954.2-17822.1 tok/s and fits up to 145k 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 145k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.