More
Best rig by budgetRent before you buySubmit a buildNewsletterFree datasetAdvertise
Submit build

Builds / 2x Nvidia GB10 (unified, DGX Spark)

2x DGX Spark: DeepSeek V4 Flash FP8 on vLLM TP2, 45.5 tok/s decode (Tech2wild)

Last updated:

Source: github.com ↗More source: github.com ↗📏 How measured: reported by the original source; RigBase re-checked the numbers at that source
Legacy models only. Every model measured on this rig now has a newer successor: DeepSeek V4 Flash → DeepSeek V4.1 Flash. The hardware numbers are still a useful reference.
GPU(s)
2x Nvidia GB10 (unified, DGX Spark)
VRAM / unified memory (GB)
256
CPU
Nvidia GB10 Grace (Arm) per node
Amazon · eBay (used) · Newegg
Motherboard
not stated
RAM
128 GB LPDDR5X unified per Spark (256 GB total)
PSU
not stated
Other
2 NVIDIA DGX Sparks, multi-node
Reported total cost
not stated
Power
not stated

Measured speed (generation tokens/sec)

ModelQuantEnginetok/sPrompt processing (tok/s)Details
DeepSeek V4 Flash legacyFP8 + MTPvLLM TP2, 2 nodes, 1 stream45.5not stated⚡ spec-decode (MTP)context: 1M📏 Single-stream decode as published in Tech2wild's recipe README (single-stream decode at 1M context (MTP n=2)).

Numbers by Tech2wild (tonyd2wild); single-stream decode at 1M context (MTP n=2). RigBase read the GitHub README on 2026-10-28 and checked each figure against the text. RigBase did not re-run it. Speculative decoding (MTP/DFlash/DSpark) inflates predictable text; these rows prefer prose/code over counting peaks. Recipe license: MIT.

Source: https://github.com/tonyd2wild/DeepSeek-V4-Flash-2x-Spark-1M
https://github.com/tonyd2wild/DeepSeek-V4-Flash-2x-Spark-1M/blob/main/README.md

Blank fields = not stated in the source. We never estimate build data; GPU street prices above are separately sourced and dated.

Embed this result

Copy into a README or blog. Links back to this build. See badge docs (CC BY 4.0 attribution). The SVG does not invent speeds — numbers stay on the build page.

Markdown

[![Measured on RigBase](https://getrigbase.com/badge/tony-2x-dgx-spark-deepseek-v4-flash-2x-spark-1m.svg)](https://getrigbase.com/builds/tony-2x-dgx-spark-deepseek-v4-flash-2x-spark-1m/)

HTML

<a href="https://getrigbase.com/builds/tony-2x-dgx-spark-deepseek-v4-flash-2x-spark-1m/" rel="noopener"><img src="https://getrigbase.com/badge/tony-2x-dgx-spark-deepseek-v4-flash-2x-spark-1m.svg" alt="Measured on RigBase" height="20"/></a>

Preview: Measured on RigBase · How to use

Rent before you buy: try this model on a cloud GPU for a few dollars first: Runpod (referral link; sign up with Google to get the new-user bonus)

Quick answers: Can 2x DGX Spark (GB10) run DeepSeek V4 Flash?