// RUN โ€” FITS

Can the AMD Radeon RX 6800 XT run CodeGen2?

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

CodeGen2 on the AMD Radeon RX 6800 XT

QuantFits?Max contextSpeedBeyond context
FP16 no โ€” โ€” โ€”
Q8 no โ€” โ€” โ€”
Q4 yes 16k 36-44 t/s ~2.8-3.4 (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 CodeGen2?โ–ถ

Yes. At Q4 it generates ~36-44 tok/s and fits up to 16k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~2.8-3.4 tok/s.

How much context fits?โ–ถ

At Q4, up to about 16k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.