Builds / 2x Nvidia GB10 (unified, DGX Spark)
2x DGX Spark: DeepSeek V4.1 Flash EXL3 2.9-bit on vLLM, 31.6 tok/s (Mia's AI Lab recipe)
Source: github.com ↗More source: mia-ai.net ↗📏 How measured: reported by the original source; RigBase re-checked the numbers at that source
- 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)
| Model | Quant | Engine | tok/s | Prompt processing (tok/s) | Details |
|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | EXL3 2.9-bit | vLLM, 2 nodes, 1 stream | 31.6 | not stated | context: 600k📏 Single-stream decode as published on Mia's AI Lab recipe card (Decode speed, one stream). Peak throughput 54 tok/s ×4 streams, speculation off. |
Recipe and numbers by Mia's AI Lab (mia-ai.net), recipe last updated 2026-09-19; RigBase read the recipe card on 2026-10-27 and checked the decode figure against the recipe README. RigBase did not re-run it. Prefill is prompt-processing speed on a 32k prompt where listed.
Source: https://github.com/MiaAI-Lab/DeepSeek-v4.1-Flash-EXL3-2x-DGX-Sparks
https://mia-ai.net/models
https://mia-ai.net/models
Blank fields = not stated in the source. We never estimate build data; GPU street prices above are separately sourced and dated.
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 V4.1 Flash?