// RUN โ€” FITS

Can the NVIDIA GeForce RTX 4060 Ti 16GB run BART-large?

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

BART-large on the NVIDIA GeForce RTX 4060 Ti 16GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 189k 258.7-308.4 t/s ~35.9-42.8 (slow)
Q8 yes 196k 517.5-616.7 t/s ~71.9-85.7 (slow)
Q4 yes 198k 924-1101.3 t/s ~128.3-153 (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 4060 Ti 16GB run BART-large?โ–ถ

Yes. At Q4 it generates ~924-1101.3 tok/s and fits up to 198k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~128.3-153 tok/s.

How much context fits?โ–ถ

At Q4, up to about 198k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.