// RUN โ€” FITS

Can the AMD Radeon Pro W7900 48GB run Nucleotide Transformer?

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

Nucleotide Transformer on the AMD Radeon Pro W7900 48GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 575k 108.9-133.1 t/s ~5-6.2 (slow)
Q8 yes 613k 217.7-266.1 t/s ~10.1-12.3 (slow)
Q4 yes 630k 388.8-475.2 t/s ~18-22 (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 Nucleotide Transformer?โ–ถ

Yes. At Q4 it generates ~388.8-475.2 tok/s and fits up to 630k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~18-22 tok/s.

How much context fits?โ–ถ

At Q4, up to about 630k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.