// RUN โ€” FITS

Can the AMD Radeon RX 9070 XT run CARP?

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

CARP on the AMD Radeon RX 9070 XT

QuantFits?Max contextSpeedBeyond context
FP16 yes 182k 315.5-385.6 t/s ~19.6-24 (slow)
Q8 yes 192k 631-771.2 t/s ~39.2-47.9 (slow)
Q4 yes 196k 1126.7-1377.1 t/s ~70-85.5 (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 AMD Radeon RX 9070 XT run CARP?โ–ถ

Yes. At Q4 it generates ~1126.7-1377.1 tok/s and fits up to 196k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~70-85.5 tok/s.

How much context fits?โ–ถ

At Q4, up to about 196k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.