// RUN โ€” FITS

Can the AMD Radeon RX 7800 XT run Gemma 3 270M?

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

Gemma 3 270M on the AMD Radeon RX 7800 XT

QuantFits?Max contextSpeedBeyond context
FP16 yes 193k 728-889.8 t/s ~46.7-57 (slow)
Q8 yes 198k 1456-1779.6 t/s ~93.3-114.1 (slow)
Q4 yes 199k 2600-3177.8 t/s ~166.7-203.7 (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 7800 XT run Gemma 3 270M?โ–ถ

Yes. At Q4 it generates ~2600-3177.8 tok/s and fits up to 199k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~166.7-203.7 tok/s.

How much context fits?โ–ถ

At Q4, up to about 199k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.