// RUN โ€” FITS

Can the AMD Radeon RX 6900 XT run SmolLM-1.7B?

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

SmolLM-1.7B on the AMD Radeon RX 6900 XT

QuantFits?Max contextSpeedBeyond context
FP16 yes 150k 94.3-115.3 t/s ~7.4-9 (slow)
Q8 yes 176k 188.6-230.5 t/s ~14.7-18 (slow)
Q4 yes 187k 336.8-411.7 t/s ~26.3-32.2 (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 6900 XT run SmolLM-1.7B?โ–ถ

Yes. At Q4 it generates ~336.8-411.7 tok/s and fits up to 187k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~26.3-32.2 tok/s.

How much context fits?โ–ถ

At Q4, up to about 187k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.