---
type: "Article"
title: "Qwen3.8-Flash-Next NVFP4 with vLLM (b12x) on 1× DGX Spark"
description: "Qwen3.8-Flash-Next NVFP4 with vLLM (b12x) on 1× DGX Spark: recipe by vcruz305 with speed, condition and source for every number, weights and license."
resource: "https://www.contextstudios.ai/local-ai/vcruz305--qwen38-flash-next-nvfp4-1spark-vllm-b12x"
language: "en"
generated:
  by: "process:contextstudios-md/1"
  at: "2026-11-11T03:21:05.359Z"
status: "stable"
---

# Qwen3.8-Flash-Next NVFP4 with vLLM (b12x) on 1× DGX Spark

Qwen3.8-Flash-Next NVFP4 with vLLM (b12x) on 1× DGX Spark: 68.1 tok/s according to github.com (dataset as of Nov 3, 2026).

- Creator: [vcruz305](https://www.contextstudios.ai/local-ai/creators/vcruz305.md)
- Engine: vLLM im Container eugr/spark-vllm-b12x (Digest sha256:03a95654), MTP k=4
- Quantization: NVFP4+csf (NVIDIA FP4-Local, QAD), FP8 KV, PLE-n-gram-Tabelle von NVMe
- Model family: Qwen3.8-Flash-Next
- Hardware: dgx-spark x1
- Context: 262144
- Artificial Analysis Intelligence Index: 39.8 ([source](https://artificialanalysis.ai/models/qwen3-8-flash-next))

## All numbers

- 68.1 tok/s (Peak; Peak, 1 request, synthetic speed suite (p50), with MTP (per recipe)) — [source](https://github.com/vcruz305/Qwen3.8-Flash-Next-FP4-Spark-recipe#measured-speed-client-observed-this-route-exposes-no-server-metrics)
- decode_tps: 68.06 (1 request) — [source](https://github.com/vcruz305/Qwen3.8-Flash-Next-FP4-Spark-recipe#measured-speed-client-observed-this-route-exposes-no-server-metrics)

## Weights

- [nvidia/Qwen3.8-Flash-Next-FP4-Local](https://huggingface.co/nvidia/Qwen3.8-Flash-Next-FP4-Local) (main, other)
- [Qwen/Qwen3.8-Flash-Next](https://huggingface.co/Qwen/Qwen3.8-Flash-Next) (base, other)

[https://github.com/vcruz305/Qwen3.8-Flash-Next-FP4-Spark-recipe](https://github.com/vcruz305/Qwen3.8-Flash-Next-FP4-Spark-recipe)

## Related

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