---
title: "Qwen 3.8 Flash-Next will have to be quantized down to 4 bit precision or lower in order to fit..."
date: 2026-08-26
canonical: https://solmaz.io/x/2092620316065366527/
x_url: https://x.com/onusoz/status/2092620316065366527
license: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)
---

Qwen 3.8 Flash-Next will have to be quantized down to 4 bit precision or lower in order to fit a DGX Spark and leave some leeway

Excited to see the performance on the Spark

*Quotes a post by @kimmonismus (https://x.com/kimmonismus/status/2092593917543780735); its text is omitted here because it is not covered by this site's license.*