ModelDock / hardware record

DGX Spark local AI benchmarks

Compare the published model-specific reading / prefill and single-stream writing / decode results for DGX Spark.

Memory128 GBPublished model records: 2

Available model records

DGX Spark performance by model

ModelReading / prefillWriting / decodeEvidenceAs of

Qwen3.8 27Bqwen38_27b_c1_personal

1,225.5 tok/s

44 tok/s

Source-backed

2026-08-24

Qwen3.8 Flash Nextqwen38_flash_next_c1_personal

540.1 tok/s

21.1 tok/s

Source-backed

2026-08-28

Reading / prefill

Prefill · tok/s

Writing / decode

Decode · single stream · tok/s

Evidence

Each row is one hardware × model record. Source observations stay on Evidence; projections link to their calibration details on Data.