// RUN โ€” FITS

Can the AMD Radeon Pro W7900 48GB run EXAONE 3.5 7.8B?

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

EXAONE 3.5 7.8B on the AMD Radeon Pro W7900 48GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 206k 34.9-42.6 t/s ~1.6-2 (slow)
Q8 yes 266k 69.8-85.3 t/s ~3.2-3.9 (slow)
Q4 yes 292k 124.6-152.3 t/s ~5.8-7.1 (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 Pro W7900 48GB run EXAONE 3.5 7.8B?โ–ถ

Yes. At Q4 it generates ~124.6-152.3 tok/s and fits up to 292k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~5.8-7.1 tok/s.

How much context fits?โ–ถ

At Q4, up to about 292k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.