---
type: "Article"
title: "Qwen3.8-Flash-Next 125B NVFP4 mit TensorFold auf 2× DGX Spark (1M Kontext)"
description: "Qwen3.8-Flash-Next 125B NVFP4 mit TensorFold auf 2× DGX Spark (1M Kontext): Rezept von MiaAI-Lab mit Tempo, Bedingung und Quelle je Zahl, Gewichten und Lizenz."
resource: "https://www.contextstudios.ai/de/lokale-ki/miaai-lab--qwen3.8-flash-dual-dgx-sparks-tensorfold"
language: "de"
generated:
  by: "process:contextstudios-md/1"
  at: "2026-10-24T17:10:18.078Z"
status: "stable"
---

# Qwen3.8-Flash-Next 125B NVFP4 mit TensorFold auf 2× DGX Spark (1M Kontext)

Qwen3.8-Flash-Next 125B NVFP4 mit TensorFold auf 2× DGX Spark (1M Kontext): 67,4 tok/s laut github.com (Datensatz-Stand: 29. Sept. 2026).

- Kreator: [MiaAI-Lab](https://www.contextstudios.ai/de/lokale-ki/kreatoren/miaai-lab.md)
- Engine: TensorFold tensorfold-native (Zig, zig-flashnext db281878 + patches), Image ghcr.io/miaai-lab/qwen3.8-flash-dual-dgx-sparks-tensorfold:zig-db28187-f3e1300f4f62, TP=2 über CX7/RoCE, MTP + Copy-Drafts
- Quantisierung: NVFP4 (nvidia, Experten) + FP8 n-gram/MTP, FP8 KV
- Modellfamilie: Qwen3.8-Flash-Next
- Hardware: dgx-spark x2
- Kontext: 1048576
- Artificial Analysis Intelligence Index: 39.8 ([source](https://artificialanalysis.ai/models/qwen3-8-flash-next))

## Alle Zahlen

- 67,4 tok/s (Alltag; Alltag, 1 Anfrage, Prosa-Prompt, mit MTP (laut Rezept)) — [source](https://github.com/MiaAI-Lab/Qwen3.8-Flash-Dual-DGX-Sparks-TensorFold#performance)
- decode_tps: 67.4 (1 Anfrage) — [source](https://github.com/MiaAI-Lab/Qwen3.8-Flash-Dual-DGX-Sparks-TensorFold#performance)
- decode_tps: 390.1 (16 parallele Anfragen) — [source](https://github.com/MiaAI-Lab/Qwen3.8-Flash-Dual-DGX-Sparks-TensorFold#performance)
- prefill_tps: 2757 (1 Anfrage) — [source](https://github.com/MiaAI-Lab/Qwen3.8-Flash-Dual-DGX-Sparks-TensorFold#performance)
- ttft_ms: 104 (1 Anfrage) — [source](https://github.com/MiaAI-Lab/Qwen3.8-Flash-Dual-DGX-Sparks-TensorFold#performance)

## Gewichte

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

[https://github.com/MiaAI-Lab/Qwen3.8-Flash-Dual-DGX-Sparks-TensorFold](https://github.com/MiaAI-Lab/Qwen3.8-Flash-Dual-DGX-Sparks-TensorFold)

## Related

- [Lokale KI auf Ihrer Hardware.](https://www.contextstudios.ai/de/lokale-ki.md)