// RUN โ€” FITS

Can the NVIDIA GeForce RTX 5090 run ESM2-650M?

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

ESM2-650M on the NVIDIA GeForce RTX 5090

QuantFits?Max contextSpeedBeyond context
FP16 yes 406k 1006.3-1199.3 t/s ~22.5-26.8 (slow)
Q8 yes 416k 2012.6-2398.5 t/s ~44.9-53.5 (slow)
Q4 yes 421k 3593.8-4283.1 t/s ~80.2-95.6 (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 5090 run ESM2-650M?โ–ถ

Yes. At Q4 it generates ~3593.8-4283.1 tok/s and fits up to 421k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~80.2-95.6 tok/s.

How much context fits?โ–ถ

At Q4, up to about 421k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.