Alibaba's Qwen Team Announces Qwen3.8-Flash-Next as a Preview of Qwen4 Architecture
On August 25, Alibaba's Qwen team announced via ModelScope that its next-generation Qwen4 architecture is ready, and launched a countdown page on Hugging Face for Qwen3.8-Flash-Next, confirmed for open release on August 26. Positioned as "a preview of the Qwen4 architecture," the release drew strong community attention, with notify-me signups growing from 45 (@NielsRogge, Aug 25) to 515 (@victormustar, Aug 26).
Confirmed
- Official announcement that Qwen3.8-Flash-Next opens on August 26; the preview page shows August 26, 2026
- Open-weight multimodal mixture-of-experts (MoE) design
- 125B total parameters, including 51B N-gram parameters, with only 6B activated per token
- Built on the next-generation architecture that will underpin the upcoming Qwen4 family
- On Aug 26, @alexcovoeth relayed that the Qwen3.8-120B/51B/A6B MoE series would launch within 24 hours
- @TheZachMueller relayed that Qwen3.8 Flash is optimized for a single DGX Spark and can run in NVFP4 precision
Unconfirmed
- Whether @alexcovoeth's relay of a "Qwen3.8-120B/51B/A6B series within 24 hours" means additional models ship alongside remains officially unconfirmed
- The exact role of the 51B N-gram lookup parameters; superelesha's analysis (in @teortaxesTex's thread) awaits post-release testing
- DGX Spark deployment details come from third-party relay; precision and configuration await official confirmation
Why it matters
- Per @calabiandyau, this effectively lets developers try out Qwen4's architectural improvements early, marking another major Qwen update
- @rohanpaulai notes the large-total/small-active design targets high inference efficiency, potentially a new cost-effective open-model option if performance delivers
- The 51B N-gram lookup/embedding parameters are a rare configuration among mainstream open models, drawing attention from community members like @zephyrz9
- If the single-DGX-Spark rumor holds, local deployment barriers drop further
2026-08-25 ~ 2026-08-26 · 13 related posts
- Episode 1: Alibaba's Qwen Team Announces Qwen3.8-Flash-Next as a Preview of Qwen4 Architecture(2026-08-25, 13 posts)
- Episode 2: Alibaba Open-Sources Qwen3.8-Flash-Next, an Early Preview of the Qwen4 Architecture(2026-08-26, 26 posts)
- Episode 3: Qwen3.8-Flash ships with local deployment and claims SWE-bench Pro win over Claude(2026-08-26, 5 posts)
- Episode 4: Qwen3.8-Flash-Next FP8 Quantized Model Released on Hugging Face(2026-08-27, 2 posts)
- Episode 5: Qwen 3.8-Next Released with Detailed Technical Report(2026-08-27, 2 posts)
- Episode 6: Uncensored Qwen3.8-Flash-Next Weights and GGUF Released(2026-08-27, 2 posts)
- Episode 7: Alibaba Open-Sources Qwen3.8-Flash: 125B MoE with 6B Active Params, 20x Cheaper(2026-08-28, 7 posts)
Primary sources
- [source] Alibaba Teases Qwen4 Architecture, Announces Open Source Qwen3.8-Flash-Next — bclavie · 2026-08-25
- Qwen 3.8 Flash Next releasing: 125B params with 51B N-gram — zephyr_z9 · 2026-08-25
- Qwen Announces Qwen3.8-Flash-Next Open Source Release — cedric_chee · 2026-08-25
- Alibaba's Qwen3.8-Flash-Next releasing tomorrow with Qwen4 MoE architecture — rohanpaul_ai · 2026-08-25
- Alibaba to open-source Qwen3.8-Flash-Next, first look at architecture powering Qwen4 — calabi_and_yau · 2026-08-25
- [source] Alibaba Qwen4 architecture preview coming August 26 — NielsRogge · 2026-08-25
- Qwen 3.8 Flash Next rumored: 125B + 51B N-gram lookup tables, launches tomorrow — teortaxesTex · 2026-08-25
- Qwen3.8-Flash-Next set for Aug 26 release as a preview of Qwen4 architecture — huggingface · 2026-08-25
- Qwen3.8-Flash-Next, a preview of Qwen4 architecture, set for August 2026 release — huggingface · 2026-08-26
- Qwen3.8-120B/51B/A6B MoE models releasing in 24 hours — alexcovo_eth · 2026-08-26
- Qwen3.8-Flash-Next model coming soon — jiqizhixin · 2026-08-26
- GLM 5.3 and Qwen3.8 Flash coming soon, optimized for DGX Spark — TheZachMueller · 2026-08-26
1 near-duplicate retellings: victormustar