// RUN โ€” FITS

Can the NVIDIA GeForce RTX 5070 run CLIP (ViT L/14@336px)?

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

CLIP (ViT L/14@336px) on the NVIDIA GeForce RTX 5070

QuantFits?Max contextSpeedBeyond context
FP16 yes 134k 662.9-790.1 t/s ~39.5-47 (slow)
Q8 yes 140k 1325.8-1580.1 t/s ~78.9-94.1 (slow)
Q4 yes 142k 2367.6-2821.6 t/s ~140.9-168 (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 5070 run CLIP (ViT L/14@336px)?โ–ถ

Yes. At Q4 it generates ~2367.6-2821.6 tok/s and fits up to 142k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~140.9-168 tok/s.

How much context fits?โ–ถ

At Q4, up to about 142k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.