// RUN โ€” FITS

Can the AMD Radeon RX 9070 XT run OpenELM-3B?

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

OpenELM-3B on the AMD Radeon RX 9070 XT

QuantFits?Max contextSpeedBeyond context
FP16 yes 109k 66.7-81.6 t/s ~4.1-5.1 (slow)
Q8 yes 155k 133.5-163.1 t/s ~8.3-10.1 (slow)
Q4 yes 176k 238.3-291.3 t/s ~14.8-18.1 (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 9070 XT run OpenELM-3B?โ–ถ

Yes. At Q4 it generates ~238.3-291.3 tok/s and fits up to 176k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~14.8-18.1 tok/s.

How much context fits?โ–ถ

At Q4, up to about 176k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.