// RUN โ€” FITS

Can the NVIDIA GeForce RTX 4070 Ti Super run MSA Transformer?

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

MSA Transformer on the NVIDIA GeForce RTX 4070 Ti Super

QuantFits?Max contextSpeedBeyond context
FP16 yes 199k 2452.8-2923.2 t/s ~146-174 (slow)
Q8 yes 200k 4905.6-5846.4 t/s ~292-348 (slow)
Q4 yes 201k 8760-10440 t/s ~521.4-621.4 (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 Ti Super run MSA Transformer?โ–ถ

Yes. At Q4 it generates ~8760-10440 tok/s and fits up to 201k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~521.4-621.4 tok/s.

How much context fits?โ–ถ

At Q4, up to about 201k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.