cd/sources/hugging-face-blog· home› sources› Hugging Face Blog
cat /sources/hugging-face-blog.feed | wc -l → 1411

Hugging Face Blog

articles 1411 domain huggingface.co → page 70/71 feed RSS
14:13
2026-06-02
huggingface.co
ai-agents

Holo3.1: Fast & Local Computer Use Agents

Holo3.1, a new family of computer-use agents, is now available with improved robustness across web, desktop, and mobile environments. The release introduces quantized checkpoints for local inference, …

15:45
2026-06-01
huggingface.co
large-language-models

Introducing Mellum2: A 12B Mixture-of-Experts Model by JetBrains

JetBrains released Mellum2, a 12-billion-parameter Mixture-of-Experts model trained on natural language and code that activates only 2.5 billion parameters per token for efficient inference. The open-…

00:00
2026-05-27
huggingface.co
robotics

Reachy Mini goes fully local

Pollen Robotics and Hugging Face have released a fully local speech-to-speech pipeline for the Reachy Mini robot, eliminating the need for cloud servers or API keys. The open-source stack runs entirel…

00:00
2026-05-25
huggingface.co
ai-agents

Harness, Scaffold, and the AI Agent Terms Worth Getting Right

A new glossary from Hugging Face aims to clarify the terms "harness" and "scaffold" in AI agent development, following confusion among researchers at the ICLR 2026 conference. The glossary defines a "…

18:38
2026-05-19
huggingface.co
artificial-intelligence

OlmoEarth v1.1: A more efficient family of models

Release of OlmoEarth v1.1, a new family of transformer-based AI models designed for processing satellite imagery, which reduces compute costs by up to 3x while maintaining the performance of the origi…

00:00
2026-05-19
huggingface.co
machine-learning

Introducing the Ettin Reranker Family

The article announces the release of six new Sentence Transformers CrossEncoder reranker models, ranging from 17 million to 1 billion parameters, which are built on Ettin ModernBERT encoders and achie…

14:12
2026-05-18
huggingface.co
artificial-intelligence

The Open Agent Leaderboard

The Open Agent Leaderboard is a new open benchmark designed to evaluate the performance and cost of full AI agent systems—including their tools, planning, and error recovery—rather than just the under…

00:00
2026-05-14
huggingface.co
machine-learning

Unlocking asynchronicity in continuous batching

Synchronous continuous batching in LLM inference causes inefficiency by forcing the CPU and GPU to work sequentially, leaving one idle while the other operates. This idle time can account for nearly a…

← prev page 70 / 71 next →