Spark Bench

Independent benchmarks by Tom Hudson

DGX Spark
serving benchmarks

Find what runs on your DGX Spark setup and see how the exact configuration performed under load.

Latest benchmark · GLM-5.3 Flash2× DGX Spark · TensorFold · Decode sweep
c1
41.85
c2
54.70
c4
71.69
c8
77.02
c12
71.98
c16
73.07

Aggregate output tok/s by concurrency · ~256 input / 512 output tokens per request

14 model families · 30 configurations

What the benchmarks measure

Explore all configurations

Interactive speed

Single-stream generation speed and time to first token across a sweep of request concurrency.

Throughput under load

Aggregate output rate, latency and errors during a sustained serving test.

Context and tool use

Prompt lengths actually exercised, passkey retrieval, and published mock-tool evaluations with completion and safety-gate status.