Home/NewsUp to 3.2x Faster Inference with LFM2.5-DSparkHugging Face Blog·3 months ago☆2moAgePublishedAug 20, 2026, 4:52 PM UTCCollectedAug 20, 2026, 5:00 PM UTCRead the full article at huggingface.co↗Image: Hugging Face Blogoverfeed.news indexes and links. We publish a short excerpt — the full article stays at Hugging Face Blog.More from Hugging Face BlogLog in to follow this sourceHugging Face Blog·3 hours ago☆LLMON: An LLM-Native Markup Language, now in Granite 4.1 3B and 8B↗Hugging Face Blog·22 hours ago☆The Definitive Fine-Tuning Guide for 3D Generation Models↗Hugging Face Blog·2 days ago☆BotPsy: On-Device Personal Assistant with a Sub-Billion-Parameter Agentic Language Model↗Hugging Face Blog·2 days ago☆Token Pooling-Aware Training for Multi-Vector Embedding Models↗
Hugging Face Blog·2 days ago☆BotPsy: On-Device Personal Assistant with a Sub-Billion-Parameter Agentic Language Model↗
