Viktor.comAn AI coworker that actually does the work
Promoted
Qwen3
Think Deeper or Act Faster
5.0•21 reviews•2.7K followers
Think Deeper or Act Faster
5.0•21 reviews•2.7K followers
Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud. - QwenLM/Qwen3
This is the 22nd launch from Qwen3. View more
Qwen3.8-Flash-Next
Launching today
Qwen3.8-Flash-Next is a 125B multimodal MoE with only 6B active parameters and a new architecture built around QSA, Gated Residual, N-gram embeddings, and Muon. Its open weights give an early look at the architecture Qwen is building toward Qwen4.
Free Options
Launch Team
DeepSeek
Flowtica Scribe
Hi everyone!
Qwen has done this once before. Qwen3-Next gave everyone an early look at the architecture that later showed up in Qwen3.5.
Qwen3.8-Flash-Next is doing the same for Qwen4.
It’s a 125B model with only 6B active parameters, and a lot of the new design is about getting more capability without dragging compute up with it. QSA makes long-context retrieval cheaper, Gated Residual gives information more paths through the network, and the new N-gram memory adds capacity with very little per-token compute.
Qwen keeps putting these architecture previews out as real models people can actually run, well before the next generation arrives.
And the weights are already up :) (with a license worth reading)