Can I Run Qwen3.8-Flash-Next on NVIDIA DGX Spark?

Name: LLM Configurator — GPU VRAM Checker
Author: LLM Configurator

作者： Jakub Rusinowski · 最后更新： 2026年9月11日

Yes. Qwen3.8-Flash-Next needs 108.7 GB at Q4_K_M and the NVIDIA DGX Spark has 128 GB, leaving about 19.3 GB of headroom, at roughly 40 tok/s (estimated) with room for up to 32K of context.

The numbers

Model	Qwen3.8-Flash-Next
Parameters	180B (6B active)
Quantization	Q4_K_M
VRAM needed	108.7 GB
NVIDIA DGX Spark VRAM	128 GB
Verdict	Runs
Max context	32K
Estimated speed	~40 tok/s

What to do next

Nothing to change — run it at Q4_K_M. If you want more capability, check whether the next size up also fits.

联盟营销声明: 本页部分链接为联盟推广链接——如果你通过它们购买，LLM Configurator 可能会获得佣金，而你无需支付任何额外费用。作为亚马逊联盟成员（Amazon Associate），LLM Configurator 会从符合条件的购买中获得收益。

Running Qwen3.8-Flash-Next on this card:

NVIDIA DGX Spark (128GB)

128 GB VRAM · 150 W board power

2026年价格波动较大——请以当前商品页价格为准。

在亚马逊查看价格

Buy vs. rent Qwen3.8-Flash-Next

Buy the GPU

~$4,699

NVIDIA DGX Spark · MSRP

Rent by the hour

from $1.54/hr

2× A100 (160 GB) class

At 2 hrs/day, buying (~$4,699) beats renting at $1.54/hr after about 4.2 years.

Affiliate links — we may earn a commission if you sign up, at no extra cost to you.

Vast.ai $1.54/hr · typical low · varies

Rent on Vast.ai →

RunPod $2.78/hr

Rent on RunPod →

Cloud rates verified 2026-07 — estimates, and marketplace prices vary. Buying price is GPU MSRP only, not a full PC.

Other Qwen3.8 sizes on the NVIDIA DGX Spark

Qwen3.8-Max — does not fit (1449.0 GB)
Qwen3.8 27B — runs (16.8 GB)

Qwen3.8-Flash-Next on nearby hardware

Apple M3 Pro (36 GB) — does not fit
Apple M2 Ultra (192 GB) — runs

All Qwen3.8 sizes on the NVIDIA DGX Spark | VRAM calculator for Qwen3.8-Flash-Next | NVIDIA DGX Spark GPU page | Check your hardware