// RUN โ€” FITS

Can the NVIDIA GeForce RTX 4090 run ESM2-150M?

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

ESM2-150M on the NVIDIA GeForce RTX 4090

QuantFits?Max contextSpeedBeyond context
FP16 yes 309k 2452.8-2923.2 t/s ~97.3-116 (slow)
Q8 yes 312k 4905.6-5846.4 t/s ~194.7-232 (slow)
Q4 yes 313k 8760-10440 t/s ~347.6-414.3 (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 4090 run ESM2-150M?โ–ถ

Yes. At Q4 it generates ~8760-10440 tok/s and fits up to 313k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~347.6-414.3 tok/s.

How much context fits?โ–ถ

At Q4, up to about 313k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.