// RUN โ€” FITS

Can the AMD Radeon RX 9070 XT run Qwen3-4B?

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

Qwen3-4B on the AMD Radeon RX 9070 XT

QuantFits?Max contextSpeedBeyond context
FP16 yes 80k 50.7-62 t/s ~3.2-3.9 (slow)
Q8 yes 141k 101.4-124 t/s ~6.3-7.7 (slow)
Q4 yes 168k 181.1-221.4 t/s ~11.3-13.8 (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 9070 XT run Qwen3-4B?โ–ถ

Yes. At Q4 it generates ~181.1-221.4 tok/s and fits up to 168k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~11.3-13.8 tok/s.

How much context fits?โ–ถ

At Q4, up to about 168k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.