// RUN โ€” FITS

Can the NVIDIA GeForce RTX 4070 run LDM-1.45B?

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

LDM-1.45B on the NVIDIA GeForce RTX 4070

QuantFits?Max contextSpeedBeyond context
FP16 yes 101k 126.9-151.2 t/s ~10.1-12 (slow)
Q8 yes 123k 253.7-302.4 t/s ~20.1-24 (slow)
Q4 yes 133k 453.1-540 t/s ~36-42.9 (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 4070 run LDM-1.45B?โ–ถ

Yes. At Q4 it generates ~453.1-540 tok/s and fits up to 133k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~36-42.9 tok/s.

How much context fits?โ–ถ

At Q4, up to about 133k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.