// RUN โ€” FITS

Can the AMD Radeon RX 7900 XT run SeqVec?

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

SeqVec on the AMD Radeon RX 7900 XT

QuantFits?Max contextSpeedBeyond context
FP16 yes 255k 2709.7-3311.8 t/s ~135.5-165.6 (slow)
Q8 yes 256k 5419.4-6623.7 t/s ~271-331.2 (slow)
Q4 yes 257k 9677.4-11828 t/s ~483.9-591.4 (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 AMD Radeon RX 7900 XT run SeqVec?โ–ถ

Yes. At Q4 it generates ~9677.4-11828 tok/s and fits up to 257k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~483.9-591.4 tok/s.

How much context fits?โ–ถ

At Q4, up to about 257k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.