Does Qwen3.8 Flash Next UD-IQ4_XS fit in the NVIDIA DGX Spark (GB10)'s memory?

Estimate: the UD-IQ4_XS file is 93.7 GB and needs about 96.7 GB with an ~8K context; the NVIDIA DGX Spark (GB10) has about 96.0 GB usable, so it does not fully fit (part of it runs on the CPU).

Qwen3.8 Flash Next › NVIDIA DGX Spark (GB10)

Qwen3.8 Flash Next on the NVIDIA DGX Spark (GB10)

Qwen3.8 Flash Next runs at about 26.9 tokens/s on the NVIDIA DGX Spark (GB10) (measured, UD-IQ4_XS, CUDA, single-stream llama-server decode).

Best measured: 26.9 tokens/s generation (UD-IQ4_XS, CUDA). The source gives no prompt-processing figure.

For comparison, our size-scaling estimate for this combination is 46.6 tok/s.

Every run

Quant	Backend	Generate tok/s	Prompt tok/s	Test	Build / by / notes	Source
UD-IQ4_XS	CUDA	26.9	–	decode, llama-server, single stream	Single DGX Spark, 65K context config, temp=0, 3-run median; llama.cpp with qwen4exp support (PR #27742).	Weschera/qwen38-flashnext-single-spark (GitHub)

tg128 = generating 128 tokens; pp512 = reading a 512-token prompt (llama-bench). LocalScore averages several prompt and output lengths, so its numbers run lower than tg128. "decode, llama-server" = single-stream generation speed measured against a running llama-server (no speculative decoding).

Check prices

Amazon Newegg

As an Amazon Associate I earn from qualifying purchases.

No card yet?

Try it on a rented GPU (RunPod)

Affiliate link: if you sign up, RigBench may earn a referral credit. It never affects rankings or numbers.

All results for the NVIDIA DGX Spark (GB10) · Qwen3.8 Flash Next on other hardware

Embed this result

HTML

<a href="https://rigbench.pages.dev/model/qwen3-8-flash-next/on/nvidia-dgx-spark-gb10/"><img src="https://rigbench.pages.dev/badge/qwen3-8-flash-next--nvidia-dgx-spark-gb10.svg" alt="Qwen3.8 Flash Next · NVIDIA DGX Spark (GB10): 26.9 tok/s (UD-IQ4_XS, measured)"></a>

Markdown (GitHub README, forums)

[![Qwen3.8 Flash Next · NVIDIA DGX Spark (GB10): 26.9 tok/s (UD-IQ4_XS, measured)](https://rigbench.pages.dev/badge/qwen3-8-flash-next--nvidia-dgx-spark-gb10.svg)](https://rigbench.pages.dev/model/qwen3-8-flash-next/on/nvidia-dgx-spark-gb10/)