// RUN โ€” FITS

Can the NVIDIA GeForce RTX 4070 Super run MiniCPM-3-4B?

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

MiniCPM-3-4B on the NVIDIA GeForce RTX 4070 Super

QuantFits?Max contextSpeedBeyond context
FP16 yes 23k 46-54.8 t/s ~3.7-4.4 (slow)
Q8 yes 85k 92-109.6 t/s ~7.3-8.7 (slow)
Q4 yes 111k 164.3-195.8 t/s ~13-15.5 (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 Super run MiniCPM-3-4B?โ–ถ

Yes. At Q4 it generates ~164.3-195.8 tok/s and fits up to 111k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~13-15.5 tok/s.

How much context fits?โ–ถ

At Q4, up to about 111k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.