// RUN โ€” FITS

Can the Intel Arc A770 16GB run SmolLM-1.7B?

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

SmolLM-1.7B on the Intel Arc A770 16GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 150k 95-117.9 t/s ~6.8-8.4 (slow)
Q8 yes 176k 189.9-235.8 t/s ~13.6-16.8 (slow)
Q4 yes 187k 339.2-421.1 t/s ~24.2-30.1 (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 Intel Arc A770 16GB run SmolLM-1.7B?โ–ถ

Yes. At Q4 it generates ~339.2-421.1 tok/s and fits up to 187k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~24.2-30.1 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.