// RUN โ€” FITS

Can the NVIDIA GeForce RTX 3080 Ti run AlphaGeometry?

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

AlphaGeometry on the NVIDIA GeForce RTX 3080 Ti

QuantFits?Max contextSpeedBeyond context
FP16 yes 141k 2204.5-2627.3 t/s ~96.7-115.2 (slow)
Q8 yes 143k 4409-5254.6 t/s ~193.4-230.5 (slow)
Q4 yes 144k 7873.2-9383.2 t/s ~345.3-411.5 (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 3080 Ti run AlphaGeometry?โ–ถ

Yes. At Q4 it generates ~7873.2-9383.2 tok/s and fits up to 144k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~345.3-411.5 tok/s.

How much context fits?โ–ถ

At Q4, up to about 144k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.