// RUN โ€” FITS

Can the AMD Radeon RX 6800 XT run CodeT5-base?

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

CodeT5-base on the AMD Radeon RX 6800 XT

QuantFits?Max contextSpeedBeyond context
FP16 yes 195k 733.1-896 t/s ~57.3-70 (slow)
Q8 yes 198k 1466.2-1792 t/s ~114.5-140 (slow)
Q4 yes 200k 2618.2-3200 t/s ~204.5-250 (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 6800 XT run CodeT5-base?โ–ถ

Yes. At Q4 it generates ~2618.2-3200 tok/s and fits up to 200k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~204.5-250 tok/s.

How much context fits?โ–ถ

At Q4, up to about 200k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.