// RUN โ€” FITS

Can the AMD Instinct MI300X 192GB run Evo?

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

Evo on the AMD Instinct MI300X 192GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 1229k 238.5-291.5 t/s ~1.8-2.2 (slow)
Q8 yes 1283k 477-583 t/s ~3.6-4.4 (slow)
Q4 yes 1306k 851.8-1041.1 t/s ~6.4-7.9 (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 Instinct MI300X 192GB run Evo?โ–ถ

Yes. At Q4 it generates ~851.8-1041.1 tok/s and fits up to 1306k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~6.4-7.9 tok/s.

How much context fits?โ–ถ

At Q4, up to about 1306k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.