# Qwen3.8-Flash-Next: what I've logged

> Qwen3.8-Flash-Next comes up in 2 posts of my AI log, from August 2026 to October 2026, and each item below links to the primary source. The sources come from Qwen and Alibaba, filed under open weights, agents and coding and image, video, world.

## Items

1. **Qwen3.8-Flash-Next** (Qwen, 19 Oct 2026): An open-weight experimental preview of the architecture Qwen says will underpin Qwen4: 125B parameters with 6B active, hybrid Gated DeltaNet and sparse attention, 262,144 tokens of native context. [Primary source](https://huggingface.co/Qwen/Qwen3.8-Flash-Next) · [Post](https://heyaliasif.com/ai/2026-10-20-qwen38-flash-next-deepinfer-pytorch-mps#item-1)
2. **Qwen3.8-Flash-Next** (Alibaba, 24 Aug 2026): An experimental open preview of the architecture planned for Qwen4, with 125B total and 6B active parameters. [Primary source](https://huggingface.co/Qwen/Qwen3.8-Flash-Next) · [Post](https://heyaliasif.com/ai/2026-08-24-week-in-ai#item-4)

## Posts

- 2026-10-20 [Qwen3.8-Flash-Next, DeepSeek's DeepInfer, PyTorch 2.15 on MPS](https://heyaliasif.com/ai/2026-10-20-qwen38-flash-next-deepinfer-pytorch-mps)
- 2026-08-24 [Gemini Omni 1.1 Flash video, Tencent's Hy4 and GLM-5.3-Flash open up](https://heyaliasif.com/ai/2026-08-24-week-in-ai)

Canonical: https://heyaliasif.com/ai/topics/qwen3-8-flash-next