Builds / Nvidia GB10 (unified)
DGX Spark: Ling 3.0 Flash INT4 on SGLang, 83 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
Legacy models only. Every model measured on this rig now has a newer successor: Ling 3.0 Flash → Ling 3.1 Flash. The hardware numbers are still a useful reference.
- GPU(s)
- Nvidia GB10 (unified)
- VRAM / unified memory (GB)
- 128
- CPU
- Nvidia GB10 Grace (Arm)
Amazon · eBay (used) · Newegg - Motherboard
- not stated
- RAM
- 128 GB LPDDR5X unified per Spark (128 GB total)
- PSU
- not stated
- Other
- 1 NVIDIA DGX Spark
- Reported total cost
- not stated
- Power
- not stated
Measured speed (generation tokens/sec)
| Model | Quant | Engine | tok/s | Prompt processing (tok/s) | Details |
|---|---|---|---|---|---|
| Ling 3.0 Flash legacy | INT4 + DSpark | SGLang, 1 stream | 83 | not stated | ⚡ spec-decode (DSpark)context: 256k📏 Single-stream decode as published on Mia's AI Lab recipe card (Decode speed, one stream). Peak throughput 136 tok/s ×6 streams. |
Recipe and numbers by Mia's AI Lab (mia-ai.net), recipe last updated 2026-08-25; 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/Ling-3.0-Flash-SGLang-DSpark-DGX-Spark
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)