// RUN โ€” FITS

Can the AMD Radeon Pro W7900 48GB run Segatron XL base, M=384?

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

Segatron XL base, M=384 on the AMD Radeon Pro W7900 48GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 643k 1059-1294.3 t/s ~49-59.9 (slow)
Q8 yes 647k 2118-2588.6 t/s ~98.1-119.8 (slow)
Q4 yes 649k 3782.1-4622.6 t/s ~175.1-214 (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 Segatron XL base, M=384?โ–ถ

Yes. At Q4 it generates ~3782.1-4622.6 tok/s and fits up to 649k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~175.1-214 tok/s.

How much context fits?โ–ถ

At Q4, up to about 649k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.