// RUN โ€” FITS

Can the NVIDIA GeForce RTX 2050 run LUKE?

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

LUKE on the NVIDIA GeForce RTX 2050

QuantFits?Max contextSpeedBeyond context
FP16 yes 62k 84.6-100.9 t/s ~7.6-9 (slow)
Q8 yes 69k 169.3-201.7 t/s ~15.1-18 (slow)
Q4 yes 72k 302.3-360.2 t/s ~27-32.2 (slow)

Estimate (memory-bound). Beyond "max context" the KV cache spills to SSD swap and speed drops to the "beyond" figure.

FAQ

Can the NVIDIA GeForce RTX 2050 run LUKE?โ–ถ

Yes. At Q4 it generates ~302.3-360.2 tok/s and fits up to 72k context; beyond that it spills to SSD swap and slows to ~27-32.2 tok/s.

How much context fits?โ–ถ

At Q4, up to about 72k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.