// RUN โ€” FITS

Can the NVIDIA GeForce RTX 3080 Ti run Ankh_base?

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

Ankh_base on the NVIDIA GeForce RTX 3080 Ti

QuantFits?Max contextSpeedBeyond context
FP16 yes 123k 449.8-536.1 t/s ~19.7-23.5 (slow)
Q8 yes 134k 899.7-1072.2 t/s ~39.5-47 (slow)
Q4 yes 139k 1606.6-1914.7 t/s ~70.5-84 (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 3080 Ti run Ankh_base?โ–ถ

Yes. At Q4 it generates ~1606.6-1914.7 tok/s and fits up to 139k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~70.5-84 tok/s.

How much context fits?โ–ถ

At Q4, up to about 139k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.