// RUN โ€” FITS

Can the AMD Radeon RX 6800 XT run GLIDE?

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

GLIDE on the AMD Radeon RX 6800 XT

QuantFits?Max contextSpeedBeyond context
FP16 yes 95k 46.1-56.3 t/s ~3.6-4.4 (slow)
Q8 yes 148k 92.2-112.6 t/s ~7.2-8.8 (slow)
Q4 yes 172k 164.6-201.1 t/s ~12.9-15.7 (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 6800 XT run GLIDE?โ–ถ

Yes. At Q4 it generates ~164.6-201.1 tok/s and fits up to 172k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~12.9-15.7 tok/s.

How much context fits?โ–ถ

At Q4, up to about 172k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.