FeedSources
⌘K
HF

Hugging Face Blog

61 articles total

Go to source

We’re on a journey to advance and democratize artificial intelligence through open source and open science

Go to source
  •  Measuring benchmark optimization in speech recognition
  •  Up to 3.2x Faster Inference with LFM2.5-DSpark
  •  LFM2.5 Q4\_0 Checkpoints from Quantization-Aware Distillation
  •  How Much Memory Does Your Agent Actually Need?
  •  Multi-Vector (Late Interaction) Embedding Models with Sentence Transformers
  •  Same Cluster, 33 Points More Utilization: What Changed Was the Order
  •  State of Open Models: Summer 2026 Observations
  •  Record, train, and deploy from one place with Strands Agents, LeRobot, and Hugging Face Storage Buckets
  •  What We Learned by Reproducing 2,200 papers from ICML
  •  Introducing OlmoEarth embeddings: Custom embedding exports from OlmoEarth Studio for downstream analysis
  •  LFM2.5-VL-3B for Better and Faster Vision Capabilities for the Edge
  •  Thinking of ACE? We Can Do It with Fewer Tokens
  •  Build Low-Latency Multilingual Voice Agents: Open Weights & Full Deployment Control with NVIDIA Magpie TTS
  •  Meta is back with Muse Glimmer: local, agentic, multimodal, and open source
  •  Making Knowledge Distillation Cheap Enough to Run at Scale
  •  TutorMoments: Do AI tutors know when to help and when to hold back?
  •  Baseten on Hugging Face Inference Providers 🔥
  •  Deploy local agents everywhere with LFM2.5-2.6B
  •  GPU Management: Why Idle GPUs Are the New Grounded Aircraft
  •  Anatomy of a Frontier Lab Agent Intrusion: A Technical Timeline of the July 2026 Incident