Transformers Release: v5.16.0
UpdateVerifiedAdded Sep 22, 2026
Release v5.16.0 New Model additions Qwen4-Exp Qwen4-Exp builds on Qwen3.5's hybrid text and multimodal architecture with three key components: GatedResidual (GR), Qwen Sparse Attention (QSA), and Per-Layer Embedding (PLE). GR is a Qwen-developed residual architecture that combines Hyper-Connection with GatedNorm.
Topics: Vector search, SQL, Streaming, Governance
Summaries of vendors' own notes. Product names and logos belong to their owners; logos via logo.dev.
More Transformers releases
Every Transformers release| Date | Release | Type |
|---|---|---|
| Aug 26 | Transformers Release v5.16.1 Update | Update |
| Aug 19 | Transformers Patch release: v5.15.1 Update | Update |
| Sep 10 | Transformers Release 5.17.0 Preview | Preview |
| Aug 10 | Transformers Release: v5.15.0 Update | Update |
| Jul 16 | Transformers Patch release: v5.14.1 Update | Update |
| Jul 15 | Transformers Release v5.14.0 Update | Update |
| Jul 11 | Transformers Patch release v5.13.1 Update | Update |
| Jul 3 | Transformers Release v5.13.0 Update | Update |
