// RUN โ€” FITS

Can the NVIDIA GeForce RTX 5080 run TiTok-L?

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

TiTok-L on the NVIDIA GeForce RTX 5080

QuantFits?Max contextSpeedBeyond context
FP16 yes 192k 1141.4-1360.3 t/s ~47.6-56.7 (slow)
Q8 yes 197k 2282.7-2720.5 t/s ~95.1-113.4 (slow)
Q4 yes 199k 4076.3-4858.1 t/s ~169.8-202.4 (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 5080 run TiTok-L?โ–ถ

Yes. At Q4 it generates ~4076.3-4858.1 tok/s and fits up to 199k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~169.8-202.4 tok/s.

How much context fits?โ–ถ

At Q4, up to about 199k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.