// RUN โ€” FITS

Can the NVIDIA DGX Spark run Infinity?

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

Infinity on the NVIDIA DGX Spark

QuantFits?Max contextSpeedBeyond context
FP16 yes 1674k 49.8-59.4 t/s ~1.8-2.2 (slow)
Q8 yes 1704k 99.6-118.8 t/s ~3.7-4.4 (slow)
Q4 yes 1718k 177.9-212.1 t/s ~6.5-7.8 (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 Infinity?โ–ถ

Yes. At Q4 it generates ~177.9-212.1 tok/s and fits up to 1718k context; beyond that it spills to SSD swap and slows to ~6.5-7.8 tok/s.

How much context fits?โ–ถ

At Q4, up to about 1718k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.