Nov 12, 2026 · 9 min read · Small Models on One DGX Spark Before Any Benchmark: Can Five Open Models Run Well on One DGX Spark? T01: all five models kept a 32k-token prompt intact and finished a 5-call tool chain. The four MoE models decode at 52–66 tok/s; the dense Qwen3.8-27B manages 21. Small Models on One DGX Spark DGX Spark LLM Evaluation Local LLMs