// RUN โ€” FITS

Can the NVIDIA DGX Spark run S4?

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

S4 on the NVIDIA DGX Spark

QuantFits?Max contextSpeedBeyond context
FP16 yes 1727k 400.2-476.9 t/s ~14.7-17.5 (slow)
Q8 yes 1731k 800.4-953.9 t/s ~29.3-34.9 (slow)
Q4 yes 1733k 1429.2-1703.3 t/s ~52.4-62.4 (slow)

Estimate (memory-bound). Beyond "max context" the KV cache spills to SSD swap and speed drops to the "beyond" figure.

FAQ

Can the NVIDIA DGX Spark run S4?โ–ถ

Yes. At Q4 it generates ~1429.2-1703.3 tok/s and fits up to 1733k context; beyond that it spills to SSD swap and slows to ~52.4-62.4 tok/s.

How much context fits?โ–ถ

At Q4, up to about 1733k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.