// RUN โ€” FITS

Can the AMD Radeon RX 7900 XT run ESM1-43M?

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

ESM1-43M on the AMD Radeon RX 7900 XT

QuantFits?Max contextSpeedBeyond context
FP16 yes 257k 5915.5-7230 t/s ~295.8-361.5 (slow)
Q8 yes 257k 11831-14460.1 t/s ~591.5-723 (slow)
Q4 yes 258k 21126.8-25821.6 t/s ~1056.3-1291.1 (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 RX 7900 XT run ESM1-43M?โ–ถ

Yes. At Q4 it generates ~21126.8-25821.6 tok/s and fits up to 258k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~1056.3-1291.1 tok/s.

How much context fits?โ–ถ

At Q4, up to about 258k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.