DeepSeek v4 Flash Hits 82 tok/s on Dual DGX Sparks
andrewchen · x · 2026-08-02
A developer shared benchmarks running DeepSeek v4 Flash (0731) on two NVIDIA DGX Sparks. Using official FP8 weights, single-stream throughput reaches 82 tok/s (peaking at 95 tok/s), and 135 tok/s across 3 concurrent sessions. The deployment recipe is open-sourced.
Related event: DeepSeek-V4-Flash Local Deployment Benchmarks: Performance Across Hardware(21 posts)→
More from Infra
- Running 2.78T Parameter Kimi K3 on a Single CPU with 8GB RAM — Saboo_Shubham_ · 2026-08-03
- AMD Enters Open-Source LLM Arena with Instella-MoE-16B — airesearch12 · 2026-08-03
- US States Move to Repeal Data Center Tax Breaks, Raising AI Infrastructure Costs — pstAsiatech · 2026-08-03
- Handling Offline AI Jobs: Developers Share Best Engineering Practices — cmm324 · 2026-08-03
- A 10-Week Roadmap for LLM Inference Serving and Optimization — _jaydeepkarale · 2026-08-03
- App Developers Should Ship Their Own On-Device Models — abacaj · 2026-08-03