Dual DGX Spark Setup Hits 40 tok/s on DeepSeek Locally
Teknium · x · 2026-08-09
Developer Teknium shared real-world benchmarks for local AI deployment using NVIDIA DGX Spark. By connecting two Spark units with a single cable, he achieved around 40 tok/s running an uncensored DeepSeek model without extra acceleration frameworks. This enables completely private, local inference. He also expressed hope that the upcoming Spark 2 will feature 512GB of memory.
Related event: Dual Spark Runs Abliterated DeepSeek Locally at 40 tok/s(3 posts)→
More from Infra
- MLCommons launches MLPerf Endpoints, a benchmark that measures inference endpoints the way buyers actually purchase them — TheKanter · 2026-10-16
- Neocloud M&A decoded: CoreWeave, Nebius, Crusoe, Nscale all bet margins vanish beyond GPU scarcity — AccBalanced · 2026-10-16
- AI-Driven Timing-Aware Power Optimization Uses Learned Ranking With Baseline-Preserving Repair — Amit Sharma · 2026-10-16
- Nscale AI datacenter plagued by coolant leaks, transformer fire, 10 safety violations — saranormous · 2026-10-16
- WSL 3.0 ships with native containers and Linux 6.18 kernel, syscall overhead down ~16% — solyarisoftware · 2026-10-16
- Are 22 GB modded RTX 2080 Ti cards a viable budget local LLM option? — Dave86ch · 2026-10-16