// RUN — FITS

Can the NVIDIA DGX Spark run Qwen3-8B?

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

Qwen3-8B on the NVIDIA DGX Spark

QuantFits?Max contextSpeedBeyond context
FP16 yes 742k 12.2-14.5 t/s ~0.4-0.5 (slow)
Q8 yes 805k 24.3-29 t/s ~0.9-1.1 (slow)
Q4 yes 832k 43.4-51.7 t/s ~1.6-1.9 (slow)

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

→ All models on the NVIDIA DGX Spark → Qwen3-8B specs → Other hardware

FAQ

Can the NVIDIA DGX Spark run Qwen3-8B?▶

Yes. At Q4 it generates ~43.4-51.7 tok/s and fits up to 832k context; beyond that it spills to SSD swap and slows to ~1.6-1.9 tok/s.

How much context fits?▶

At Q4, up to about 832k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.