// RUN — FITS

Can the AMD Radeon RX 7900 XTX run Orion Star (猎户星空大模型)?

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

Orion Star (猎户星空大模型) on the AMD Radeon RX 7900 XTX

QuantFits?Max contextSpeedBeyond context
FP16 no
Q8 yes 40k 43.2-52.8 t/s ~1.8-2.2 (slow)
Q4 yes 78k 77.1-94.3 t/s ~3.2-3.9 (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 7900 XTX run Orion Star (猎户星空大模型)?

Yes. At Q4 it generates ~77.1-94.3 tok/s and fits up to 78k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~3.2-3.9 tok/s.

How much context fits?

At Q4, up to about 78k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.