// RUN โ€” FITS

Can the NVIDIA GeForce RTX 4070 Super run Phi-4-Multimodal?

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

Phi-4-Multimodal on the NVIDIA GeForce RTX 4070 Super

QuantFits?Max contextSpeedBeyond context
FP16 no โ€” โ€” โ€”
Q8 yes 30k 65.7-78.3 t/s ~5.2-6.2 (slow)
Q4 yes 49k 117.3-139.8 t/s ~9.3-11.1 (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 Phi-4-Multimodal?โ–ถ

Yes. At Q4 it generates ~117.3-139.8 tok/s and fits up to 49k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~9.3-11.1 tok/s.

How much context fits?โ–ถ

At Q4, up to about 49k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.