// RUN โ€” FITS

Can the AMD Radeon RX 7800 XT run Tk-Instruct?

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

Tk-Instruct on the AMD Radeon RX 7800 XT

QuantFits?Max contextSpeedBeyond context
FP16 no โ€” โ€” โ€”
Q8 yes 14k 35.7-43.7 t/s ~2.3-2.8 (slow)
Q4 yes 43k 63.8-78 t/s ~4.1-5 (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 Tk-Instruct?โ–ถ

Yes. At Q4 it generates ~63.8-78 tok/s and fits up to 43k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~4.1-5 tok/s.

How much context fits?โ–ถ

At Q4, up to about 43k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.