Builds / Nvidia GB10 (unified)

DGX Spark: Qwen3.8 Flash-Next NVFP4 on vLLM, 48.7 tok/s (Mia's AI Lab recipe)

Last updated: 28 Oct 2026

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): 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
Qwen3.8 Flash-Next	NVFP4	vLLM, 1 stream	48.7	1,769 @ 32k-token prompt est. TTFT @8k ≈ 4.6 s (calculated from measured prefill)	context: 262k · 512k with YaRN📏 Single-stream decode as published on Mia's AI Lab recipe card (Decode speed, one stream). Peak throughput 163 tok/s ×8 streams.

Prompt processing = prefill speed (how fast the prompt is read) as reported by the source, with the prompt length it was measured at; blank = the source does not report it. est. TTFT @8k is calculated from the measured prefill speed (8,192 ÷ prefill tok/s), shown only when prefill was measured on a prompt of 512+ tokens. It is not a measurement and ignores load time and caching. measured TTFT is the source's own time-to-first-token. Why prefill matters for coding assistants.

Recipe and numbers by Mia's AI Lab (mia-ai.net), recipe last updated 2026-10-04; RigBase read the recipe card on 2026-10-28 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/Qwen3.8-Flash-Next-Single-DGX-Spark
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.

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/mia-dgx-spark-qwen3-8-flash-next-single-dgx-spark.svg)](https://getrigbase.com/builds/mia-dgx-spark-qwen3-8-flash-next-single-dgx-spark/)

HTML

<a href="https://getrigbase.com/builds/mia-dgx-spark-qwen3-8-flash-next-single-dgx-spark/" rel="noopener"><img src="https://getrigbase.com/badge/mia-dgx-spark-qwen3-8-flash-next-single-dgx-spark.svg" alt="Measured on RigBase" height="20"/></a>

Preview: · 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 DGX Spark (GB10) run Qwen3.8 Flash-Next?