---
type: "Article"
title: "Qwen3.8-27B NVFP4 with Atlas on 1× DGX Spark"
description: "Qwen3.8-27B NVFP4 with Atlas on 1× DGX Spark: recipe by Weschera with speed, condition and source for every number, weights and license."
resource: "https://www.contextstudios.ai/local-ai/weschera--qwen38-27b-nvfp4-atlas-mtp3-1x-dgx-spark"
language: "en"
generated:
  by: "process:contextstudios-md/1"
  at: "2026-10-02T15:05:42.199Z"
status: "stable"
---

# Qwen3.8-27B NVFP4 with Atlas on 1× DGX Spark

Qwen3.8-27B NVFP4 with Atlas on 1× DGX Spark: 19 tok/s according to github.com (dataset as of Sep 29, 2026).

- Creator: [Weschera](https://www.contextstudios.ai/local-ai/creators/weschera.md)
- Engine: Atlas
- Quantization: NVFP4 (unsloth); MTP-Head bf16 (--mtp-quantization bf16); fp8 KV (Engine-Default)
- Model family: Qwen3.8-27B
- Hardware: dgx-spark x1
- Context: 32768

## All numbers

- 19 tok/s (Everyday; Everyday, 1 request, prose prompt, with MTP (per recipe)) — [source](https://github.com/Weschera/Atlas-DGX-Spark-Quickstart/blob/main/README.md)
- decode_tps: 19 (1 request) — [source](https://github.com/Weschera/Atlas-DGX-Spark-Quickstart/blob/main/README.md)
- decode_tps: 31.6 (1 request) — [source](https://github.com/Weschera/Qwen3.8-27B-DGX-Spark-Quant-Ladder/blob/main/README.md)

## Weights

- [unsloth/Qwen3.8-27B-NVFP4](https://huggingface.co/unsloth/Qwen3.8-27B-NVFP4) (main, apache-2.0)

[https://github.com/Weschera/Atlas-DGX-Spark-Quickstart](https://github.com/Weschera/Atlas-DGX-Spark-Quickstart)

## Related

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