// RUN โ€” FITS

Can the NVIDIA GeForce RTX 4070 Ti Super run Persimmon-8B?

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

Persimmon-8B on the NVIDIA GeForce RTX 4070 Ti Super

QuantFits?Max contextSpeedBeyond context
FP16 no โ€” โ€” โ€”
Q8 yes 30k 52.7-62.9 t/s ~3.1-3.7 (slow)
Q4 yes 61k 94.2-112.3 t/s ~5.6-6.7 (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 Persimmon-8B?โ–ถ

Yes. At Q4 it generates ~94.2-112.3 tok/s and fits up to 61k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~5.6-6.7 tok/s.

How much context fits?โ–ถ

At Q4, up to about 61k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.