Models & Labs
Hugging Face Releases Ettin Reranker Models
Hugging Face Bloghigh confidence
Why it matters
- →Enhances search accuracy by reordering retrieved documents with high precision.
- →Supports long-context processing, accommodating up to 8,192 tokens.
- →Offers significant speed improvements, making it practical for real-world applications.
Hugging Face has introduced six new Sentence Transformers CrossEncoder rerankers, built on Ettin ModernBERT encoders. These models, ranging from 17 million to 1 billion parameters, are designed to improve search accuracy by reordering retrieved documents. They support long-context processing with up to 8,192 tokens and offer significant speed improvements. This release provides developers with advanced tools to enhance AI-driven search systems.
Read originalThe story around this
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
What happened next
- 1Hugging Face Models Used for Nonconsensual Deepfakes
The Verge AI · July 28, 2026 · Background
- 2
More from Hugging Face Blog
More in Models & Labs
Models & Labsmodels
llama.cpp b12029 adds CUDA 13 and Snapdragon support
This release quietly cements llama.cpp as the universal inference runtime by finally supporting NVIDIA's latest CUDA 13 stack alongside AMD's ROCm 10.0. The inclusion of native builds for Linux arm64 with Snapdragon chips, covering CPU, Adreno GPU, and Hexagon NPU, signals a serious push into mobile edge deployment. While Apple Silicon KleidiAI is disabled in this specific build, the broader hardware coverage means developers no longer need to compile from source for most modern accelerators. It’s less about new features and more about removing friction for anyone running local models on bleeding-edge or diverse hardware.
llama.cpp Releases
© The Verge AIModels & Labsother
