// RUN โ€” FITS

Can the NVIDIA GeForce RTX 4070 Super run Otter?

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

Otter on the NVIDIA GeForce RTX 4070 Super

QuantFits?Max contextSpeedBeyond context
FP16 yes 106k 141.5-168.6 t/s ~11.2-13.4 (slow)
Q8 yes 126k 283-337.3 t/s ~22.5-26.8 (slow)
Q4 yes 134k 505.4-602.3 t/s ~40.1-47.8 (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 Otter?โ–ถ

Yes. At Q4 it generates ~505.4-602.3 tok/s and fits up to 134k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~40.1-47.8 tok/s.

How much context fits?โ–ถ

At Q4, up to about 134k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.