// RUN โ€” FITS

Can the AMD Instinct MI300X 192GB run 6-Act Tether?

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

6-Act Tether on the AMD Instinct MI300X 192GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 2672k 333900-408100 t/s ~2520-3080 (slow)
Q8 yes 2672k 667800-816200 t/s ~5040-6160 (slow)
Q4 yes 2672k 1192500-1457500 t/s ~9000-11000 (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 Instinct MI300X 192GB run 6-Act Tether?โ–ถ

Yes. At Q4 it generates ~1192500-1457500 tok/s and fits up to 2672k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~9000-11000 tok/s.

How much context fits?โ–ถ

At Q4, up to about 2672k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.