---
type: "Article"
title: "Qwen3.8-Flash-Next 125B INT4-AutoRound mit TensorFold auf 1× DGX Spark"
description: "Qwen3.8-Flash-Next 125B INT4-AutoRound mit TensorFold auf 1× DGX Spark: 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-next-single-dgx-spark-tensorfold"
language: "de"
generated:
  by: "process:contextstudios-md/1"
  at: "2026-10-24T18:06:10.771Z"
status: "stable"
---

# Qwen3.8-Flash-Next 125B INT4-AutoRound mit TensorFold auf 1× DGX Spark

Qwen3.8-Flash-Next 125B INT4-AutoRound mit TensorFold auf 1× DGX Spark: 64,4 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 tensorfold-qwen38:zig-db28187, MTP-Drafts
- Quantisierung: INT4-AutoRound (GPTQ int4, Top-5-Experten) + FP8 n-gram-Tabelle, FP8 KV
- Modellfamilie: Qwen3.8-Flash-Next
- Hardware: dgx-spark x1
- Kontext: 262144

## Alle Zahlen

- 64,4 tok/s (Alltag; Alltag, 1 Anfrage, Prosa-Prompt, mit MTP (laut Rezept)) — [source](https://github.com/MiaAI-Lab/Qwen3.8-Flash-Next-Single-DGX-Spark-TensorFold#performance)
- decode_tps: 64.4 (1 Anfrage) — [source](https://github.com/MiaAI-Lab/Qwen3.8-Flash-Next-Single-DGX-Spark-TensorFold#performance)
- decode_tps: 200.9 (8 parallele Anfragen) — [source](https://github.com/MiaAI-Lab/Qwen3.8-Flash-Next-Single-DGX-Spark-TensorFold#performance)
- prefill_tps: 2643 (1 Anfrage) — [source](https://github.com/MiaAI-Lab/Qwen3.8-Flash-Next-Single-DGX-Spark-TensorFold#performance)
- ttft_ms: 98 (1 Anfrage) — [source](https://github.com/MiaAI-Lab/Qwen3.8-Flash-Next-Single-DGX-Spark-TensorFold#performance)

## Gewichte

- [azampatti/Qwen3.8-Flash-Next-125B-A5B-INT4-AutoRound](https://huggingface.co/azampatti/Qwen3.8-Flash-Next-125B-A5B-INT4-AutoRound) (main, other)
- [Qwen/Qwen3.8-Flash-Next](https://huggingface.co/Qwen/Qwen3.8-Flash-Next) (base, other)
- [Intel/Qwen3.8-Flash-Next-W4A16-AutoRound](https://huggingface.co/Intel/Qwen3.8-Flash-Next-W4A16-AutoRound) (other, other)
- [Saren/Qwen3.8-Flash-Next-ple-table-fp8](https://huggingface.co/Saren/Qwen3.8-Flash-Next-ple-table-fp8) (other, other)

[https://github.com/MiaAI-Lab/Qwen3.8-Flash-Next-Single-DGX-Spark-TensorFold](https://github.com/MiaAI-Lab/Qwen3.8-Flash-Next-Single-DGX-Spark-TensorFold)

## Related

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