// RUN โ€” FITS

Can the AMD Radeon RX 7900 XT run EXAONE Deep 2.4B?

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

EXAONE Deep 2.4B on the AMD Radeon RX 7900 XT

QuantFits?Max contextSpeedBeyond context
FP16 yes 185k 105-128.3 t/s ~5.3-6.4 (slow)
Q8 yes 221k 210-256.7 t/s ~10.5-12.8 (slow)
Q4 yes 237k 375-458.3 t/s ~18.8-22.9 (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 EXAONE Deep 2.4B?โ–ถ

Yes. At Q4 it generates ~375-458.3 tok/s and fits up to 237k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~18.8-22.9 tok/s.

How much context fits?โ–ถ

At Q4, up to about 237k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.