Can 2x DGX Spark (GB10) run DeepSeek V4 Flash?
Last updated:
Yes. Measured 62.48 tok/s generation (vLLM TP2, 2 nodes, 1 stream, FP8 + DSpark; source).
Every measured result for DeepSeek V4 Flash on 2x DGX Spark (GB10)
| Build | Quant / setup | Engine | tok/s | |
|---|---|---|---|---|
| 2x DGX Spark: DeepSeek V4 Flash FP8 on vLLM TP2, 62.48 tok/s code (Tech2wild) | FP8 + DSpark | vLLM TP2, 2 nodes, 1 stream | 62.48 | source |
| 2x DGX Spark: DeepSeek V4 Flash FP8 on vLLM TP2, 45.5 tok/s decode (Tech2wild) | FP8 + MTP | vLLM TP2, 2 nodes, 1 stream | 45.5 | source |
Speeds are decode (generation) tokens/sec as reported by each source; quant, engine and context differ, so small gaps are noise.
All measured speeds for DeepSeek V4 Flash: best home rig for DeepSeek V4 Flash.
DeepSeek V4 Flash on other hardware: 8x RTX 3090
Other models measured on 2x DGX Spark (GB10): DeepSeek V4.1 Flash · GLM-5.3 Flash · MiMo V2.6 Flash · MiniMax M3.1 Flash · Qwen3.8 Flash-Next
Not enough VRAM? Rent before you buy. Run DeepSeek V4 Flash on a bigger GPU on a rented 24–96 GB cloud GPU by the hour and see the real speed before spending €1,000+. Try it on Runpod
Referral link: if you sign up with Google and add $10, Runpod gives you and RigBase bonus credit (terms). It never affects our data.
Referral link: if you sign up with Google and add $10, Runpod gives you and RigBase bonus credit (terms). It never affects our data.