// RUN โ€” FITS

Can the AMD Radeon Pro W7900 48GB run Viking?

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

Viking on the AMD Radeon Pro W7900 48GB

QuantFits?Max contextSpeedBeyond context
FP16 no โ€” โ€” โ€”
Q8 yes 37k 16.5-20.2 t/s ~0.8-0.9 (slow)
Q4 yes 92k 29.5-36 t/s ~1.4-1.7 (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 Viking?โ–ถ

Yes. At Q4 it generates ~29.5-36 tok/s and fits up to 92k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~1.4-1.7 tok/s.

How much context fits?โ–ถ

At Q4, up to about 92k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.