// RUN โ€” FITS

Can the AMD Instinct MI300X 192GB run CamemBERT?

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

CamemBERT on the AMD Instinct MI300X 192GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 2662k 4983.6-6091 t/s ~37.6-46 (slow)
Q8 yes 2667k 9967.2-12182.1 t/s ~75.2-91.9 (slow)
Q4 yes 2670k 17798.5-21753.7 t/s ~134.3-164.2 (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 CamemBERT?โ–ถ

Yes. At Q4 it generates ~17798.5-21753.7 tok/s and fits up to 2670k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~134.3-164.2 tok/s.

How much context fits?โ–ถ

At Q4, up to about 2670k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.