---
type: "Article"
title: "Qwen3.8-Flash-Next NVFP4 with SparkRing on 4× DGX Spark"
description: "Qwen3.8-Flash-Next NVFP4 with SparkRing on 4× DGX Spark: recipe by fujitsupolycom with speed, condition and source for every number, weights and license."
resource: "https://www.contextstudios.ai/local-ai/fujitsupolycom--qwen38-flash-next-nvfp4-qad-tp4-4x-dgx-spark"
language: "en"
generated:
  by: "process:contextstudios-md/1"
  at: "2026-10-24T16:16:57.252Z"
status: "stable"
---

# Qwen3.8-Flash-Next NVFP4 with SparkRing on 4× DGX Spark

Qwen3.8-Flash-Next NVFP4 with SparkRing on 4× DGX Spark: 64 tok/s according to github.com (dataset as of Sep 29, 2026).

- Creator: [fujitsupolycom](https://www.contextstudios.ai/local-ai/creators/fujitsupolycom.md)
- Engine: vLLM (local-inference-lab Fork) via SparkRing (switchless NCCL ueber ConnectX-7)
- Quantization: NVFP4 QAD (Local Inference Lab)
- Model family: Qwen3.8-Flash-Next
- Hardware: dgx-spark x4
- Artificial Analysis Intelligence Index: 39.8 ([source](https://artificialanalysis.ai/models/qwen3-8-flash-next))

## All numbers

- 64 tok/s (Everyday; Everyday, 1 request, decode at 16K context (profile table), thinking on, xhigh) — [source](https://github.com/FujitsuPolycom/sparkring#profiles)
- decode_tps: 64 (1 request) — [source](https://github.com/FujitsuPolycom/sparkring#profiles)
- decode_tps: 328 (16 parallel requests) — [source](https://github.com/FujitsuPolycom/sparkring#profiles)
- prefill_tps: 4424 (1 request) — [source](https://github.com/FujitsuPolycom/sparkring#profiles)

## Weights

- [local-inference-lab/Qwen3.8-Flash-Next-NVFP4](https://huggingface.co/local-inference-lab/Qwen3.8-Flash-Next-NVFP4) (main, other)

[https://github.com/FujitsuPolycom/sparkring](https://github.com/FujitsuPolycom/sparkring)

## Related

- [Local AI on your hardware.](https://www.contextstudios.ai/local-ai.md)