llamaperf

DeepSeek V4 Flash 284B (13B active)

on 2× NVIDIA DGX Spark

Tone: positiveNVIDIA hardware
Oct 6, 2026
Throughput
60-70 t/s gen
Quant
Native

Use cases

codingagentic

Summary

User reports DeepSeek V4 Flash 0731 running at 60-70 t/s on dual DGX Spark (ASUS GX10) with native quant. Setup uses two DGX Spark units for agent work, including porting a ~170k LOC Node codebase to Rust. The user asks what others use for coordinating multiple agents with local models.