---
type: "Article"
title: "Qwen3.8-Flash-Next NVFP4 with SGLang on 2× DGX Spark"
description: "Qwen3.8-Flash-Next NVFP4 with SGLang on 2× DGX Spark: recipe by Weschera with speed, condition and source for every number, weights and license."
resource: "https://www.contextstudios.ai/local-ai/weschera--qwen38-flash-next-nvfp4-radixark-nextn-2x-dgx-spark"
language: "en"
generated:
  by: "process:contextstudios-md/1"
  at: "2026-10-02T21:59:00.913Z"
status: "stable"
---

# Qwen3.8-Flash-Next NVFP4 with SGLang on 2× DGX Spark

Qwen3.8-Flash-Next NVFP4 with SGLang on 2× DGX Spark: 41.7 tok/s according to github.com (dataset as of Sep 29, 2026).

- Creator: [Weschera](https://www.contextstudios.ai/local-ai/creators/weschera.md)
- Engine: SGLang
- Quantization: NVFP4 (modelopt_fp4, RadixArk-Checkpoint); BF16 SSM; NEXTN-Draft in-checkpoint
- Model family: Qwen3.8-Flash-Next
- Hardware: dgx-spark x2
- Context: 262144

## All numbers

- 41.7 tok/s (Mixed; Mixed, 1 request, mixed prompt set, with NEXTN (MTP) (per recipe)) — [source](https://github.com/Weschera/qwen38-flashnext-dgx-spark/blob/main/README.md)
- decode_tps: 41.7 (1 request) — [source](https://github.com/Weschera/qwen38-flashnext-dgx-spark/blob/main/README.md)
- decode_tps: 49.8 (1 request) — [source](https://github.com/Weschera/qwen38-flashnext-dgx-spark/blob/main/README.md)

## Weights

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

[https://github.com/Weschera/qwen38-flashnext-dgx-spark](https://github.com/Weschera/qwen38-flashnext-dgx-spark)

## Related

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