// RUN โ€” FITS

Can the NVIDIA L40S 48GB run Ankh_base?

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

Ankh_base on the NVIDIA L40S 48GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 628k 426.2-507.9 t/s ~19.7-23.5 (slow)
Q8 yes 640k 852.3-1015.8 t/s ~39.5-47 (slow)
Q4 yes 645k 1522-1813.9 t/s ~70.5-84 (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 L40S 48GB run Ankh_base?โ–ถ

Yes. At Q4 it generates ~1522-1813.9 tok/s and fits up to 645k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~70.5-84 tok/s.

How much context fits?โ–ถ

At Q4, up to about 645k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.