---
type: "Article"
title: "Qwen3.8-Flash-Next MLX 4-bit with TensorFold on 2× DGX Spark"
description: "Qwen3.8-Flash-Next MLX 4-bit with TensorFold on 2× DGX Spark: recipe by sfxnz with speed, condition and source for every number, weights and license."
resource: "https://www.contextstudios.ai/local-ai/sfxnz--qwen38-flash-next-mlx4bit-tensorfold-2x-dgx-spark"
language: "en"
generated:
  by: "process:contextstudios-md/1"
  at: "2026-10-24T16:15:37.233Z"
status: "stable"
---

# Qwen3.8-Flash-Next MLX 4-bit with TensorFold on 2× DGX Spark

Qwen3.8-Flash-Next MLX 4-bit with TensorFold on 2× DGX Spark: 69.6 tok/s according to github.com (dataset as of Sep 29, 2026).

- Creator: [sfxnz](https://www.contextstudios.ai/local-ai/creators/sfxnz.md)
- Engine: TensorFold v0.6.2 (56e2e3e), TP=2, Image tf-qwen38-flashnext:0.6.2 (nvcr.io/nvidia/pytorch:26.07-py3)
- Quantization: MLX affine 4-bit (group 32) auf allen Linears inkl. n-gram-Tabellen und MTP-Head, KV bf16
- Model family: Qwen3.8-Flash-Next
- Hardware: dgx-spark x2
- Context: 262144
- Artificial Analysis Intelligence Index: 39.8 ([source](https://artificialanalysis.ai/models/qwen3-8-flash-next))

## All numbers

- 69.6 tok/s (Everyday; Everyday, 1 request, prose prompt, with MTP (per recipe)) — [source](https://github.com/sfxnz/Qwen3.8-Flash-Next-TensorFold-2x-DGX-Spark#measured-on-2-dgx-spark-lail-lab)
- decode_tps: 69.6 (1 request) — [source](https://github.com/sfxnz/Qwen3.8-Flash-Next-TensorFold-2x-DGX-Spark#measured-on-2-dgx-spark-lail-lab)
- decode_tps: 249.5 (1 request) — [source](https://github.com/sfxnz/Qwen3.8-Flash-Next-TensorFold-2x-DGX-Spark#measured-on-2-dgx-spark-lail-lab)
- prefill_tps: 2816 (1 request) — [source](https://github.com/sfxnz/Qwen3.8-Flash-Next-TensorFold-2x-DGX-Spark#long-context)
- ttft_ms: 50 (1 request) — [source](https://github.com/sfxnz/Qwen3.8-Flash-Next-TensorFold-2x-DGX-Spark#measured-on-2-dgx-spark-lail-lab)

## Weights

- [TensorFold/Qwen3.8-Flash-Next-MLX-4bit-MTP](https://huggingface.co/TensorFold/Qwen3.8-Flash-Next-MLX-4bit-MTP) (main, other)
- [Qwen/Qwen3.8-Flash-Next](https://huggingface.co/Qwen/Qwen3.8-Flash-Next) (base, other)

[https://github.com/sfxnz/Qwen3.8-Flash-Next-TensorFold-2x-DGX-Spark](https://github.com/sfxnz/Qwen3.8-Flash-Next-TensorFold-2x-DGX-Spark)

## Related

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