---
type: "Article"
title: "Qwen3.8-Flash-Next NVFP4/MXFP8 CSF with SparkRing on 2× DGX Spark"
description: "Qwen3.8-Flash-Next NVFP4/MXFP8 CSF with SparkRing on 2× 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-csf-tp2-2x-dgx-spark"
language: "en"
generated:
  by: "process:contextstudios-md/1"
  at: "2026-11-11T03:20:25.223Z"
status: "stable"
---

# Qwen3.8-Flash-Next NVFP4/MXFP8 CSF with SparkRing on 2× DGX Spark

Qwen3.8-Flash-Next NVFP4/MXFP8 CSF with SparkRing on 2× DGX Spark: 68 tok/s according to github.com (dataset as of Nov 3, 2026).

- Creator: [fujitsupolycom](https://www.contextstudios.ai/local-ai/creators/fujitsupolycom.md)
- Engine: vLLM (local-inference-lab Fork) via SparkRing (SIRCL-Collectives, switchless RDMA ueber ConnectX-7), Image Release 2026.10.2
- Quantization: NVFP4/MXFP8 CSF QAD (Local Inference Lab)
- Model family: Qwen3.8-Flash-Next
- Hardware: dgx-spark x2
- Context: 262144
- Artificial Analysis Intelligence Index: 39.8 ([source](https://artificialanalysis.ai/models/qwen3-8-flash-next))

## All numbers

- 68 tok/s (Everyday; Everyday, 1 request, generation at 32K context (speed table, pair), thinking on, xhigh, with MTP3 (per recipe)) — [source](https://github.com/FujitsuPolycom/sparkring#speed)
- decode_tps: 68 (1 request) — [source](https://github.com/FujitsuPolycom/sparkring#speed)
- decode_tps: 219 (8 parallel requests) — [source](https://github.com/FujitsuPolycom/sparkring#speed)
- prefill_tps: 3716 (1 request) — [source](https://github.com/FujitsuPolycom/sparkring#speed)

## Weights

- [local-inference-lab/Qwen3.8-Flash-Next-NVFP4-MXFP8-CSF-QAD](https://huggingface.co/local-inference-lab/Qwen3.8-Flash-Next-NVFP4-MXFP8-CSF-QAD) (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)