---
type: "Article"
title: "Qwen3.8-Flash-Next 125B INT4-AutoRound with TensorFold on 2× DGX Spark (1M context)"
description: "Qwen3.8-Flash-Next 125B INT4-AutoRound with TensorFold on 2× DGX Spark (1M context): recipe by MiaAI-Lab with speed, condition and source for every number, weights and license."
resource: "https://www.contextstudios.ai/local-ai/miaai-lab--qwen3.8-flash-dual-dgx-sparks-tensorfold-int4ar"
language: "en"
generated:
  by: "process:contextstudios-md/1"
  at: "2026-10-24T16:18:49.813Z"
status: "stable"
---

# Qwen3.8-Flash-Next 125B INT4-AutoRound with TensorFold on 2× DGX Spark (1M context)

Qwen3.8-Flash-Next 125B INT4-AutoRound with TensorFold on 2× DGX Spark (1M context): 89.3 tok/s according to github.com (dataset as of Sep 29, 2026).

- Creator: [MiaAI-Lab](https://www.contextstudios.ai/local-ai/creators/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 (QUANT=int4ar)
- Quantization: INT4-AutoRound (GPTQ int4, Top-5-Experten) + FP8 n-gram-Tabelle, FP8 KV
- Model family: Qwen3.8-Flash-Next
- Hardware: dgx-spark x2
- Context: 1048576

## All numbers

- 89.3 tok/s (Everyday; Everyday, 1 request, prose prompt, with MTP (per recipe)) — [source](https://github.com/MiaAI-Lab/Qwen3.8-Flash-Dual-DGX-Sparks-TensorFold#performance)
- decode_tps: 89.3 (1 request) — [source](https://github.com/MiaAI-Lab/Qwen3.8-Flash-Dual-DGX-Sparks-TensorFold#performance)
- decode_tps: 483.6 (16 parallel requests) — [source](https://github.com/MiaAI-Lab/Qwen3.8-Flash-Dual-DGX-Sparks-TensorFold#performance)
- prefill_tps: 3303 (1 request) — [source](https://github.com/MiaAI-Lab/Qwen3.8-Flash-Dual-DGX-Sparks-TensorFold#performance)
- ttft_ms: 76 (1 request) — [source](https://github.com/MiaAI-Lab/Qwen3.8-Flash-Dual-DGX-Sparks-TensorFold#performance)

## Weights

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

## Related

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