// RUN โ€” FITS

Can the NVIDIA GeForce RTX 5070 run CogView?

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

CogView on the NVIDIA GeForce RTX 5070

QuantFits?Max contextSpeedBeyond context
FP16 yes 23k 61.3-73.1 t/s ~3.7-4.4 (slow)
Q8 yes 85k 122.6-146.2 t/s ~7.3-8.7 (slow)
Q4 yes 111k 219-261 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 5070 run CogView?โ–ถ

Yes. At Q4 it generates ~219-261 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.