Nemotron 3 Nano 4B: A Compact Hybrid Model for Efficient Local AI
•
51
Community Blog & Articles
Community Articles
view all
Build a Domain-Specific Embedding Model in Under a Day
31
March 20, 2026 What's New in Mellea 0.4.0 + Granite Libraries Release
4
March 20, 2026 
State of Open Source on Hugging Face: Spring 2026
58
March 17, 2026 
Holotron-12B - High Throughput Computer Use Agent
13
March 17, 2026 
hubstorageannouncement
Introducing Storage Buckets on the Hugging Face Hub
- +8
183
March 10, 2026 
llmanalysisrl
Keep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries
- +5
71
March 10, 2026 
guidedistributed-trainingaccelerate
Ulysses Sequence Parallelism: Training with Million-Token Contexts
23
March 9, 2026 
lerobotrobotics
LeRobot v0.5.0: Scaling Every Dimension
- +6
37
March 9, 2026 Bringing Robotics AI to Embedded Platforms: Dataset Recording, VLA Fine‑Tuning, and On‑Device Optimizations
12
March 5, 2026 
open-sourcediffusersgenerative
Introducing Modular Diffusers - Composable Building Blocks for Diffusion Pipelines
44
March 5, 2026 
PRX Part 3 — Training a Text-to-Image Model in 24h!
55
March 3, 2026 
mixture-of-expertsoptimizationtransformers
Mixture of Experts (MoEs) in Transformers
- +3
141
February 26, 2026 
communityopen-sourcellm
HotGGML and llama.cpp join HF to ensure the long-term progress of Local AI
- +2
488
February 20, 2026 
llmfine-tuningtraining
Train AI models with Unsloth and Hugging Face Jobs for FREE
- +2
89
February 20, 2026 NEW Articles from Team or Enterprise organizations will get promoted to the main section.
Nemotron 3 Nano 4B: A Compact Hybrid Model for Efficient Local AI
•
51
Introducing SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding
•
38
The First Healthcare Robotics Dataset and Foundational Physical AI Models for Healthcare Robotics
•
21
Expanding the Alpamayo Open Platform for Developing Reasoning AVs Across Models, Data, and Simulation
•
17
**LoRA Fine-Tuning BitNet b1.58 LLMs on Heterogeneous Edge GPUs via QVAC Fabric**
•
11
NEO-unify: Building Native Multimodal Unified Models End to End
•
103
ATE-2: State-of-the-Art Armenian Text Embeddings and the ArmBench-TextEmbed Benchmark
•
8
Raw Robot Video to VLA-Ready Training Data: Annotating LeRobot Datasets with Nomadic and HuggingFace Buckets
•
8
KV Caching Explained: Optimizing Transformer Inference Efficiency
•
250
Beyond Semantic Similarity: Introducing NVIDIA NeMo Retriever’s Generalizable Agentic Retrieval Pipeline
•
36
Introducing AI chunking to semchunk
•
7
Uncensor any LLM with abliteration
•
812
SynthVision: Building a 110K Synthetic Medical VQA Dataset with Cross-Model Validation
•
6
From GRPO to DAPO and GSPO: What, Why, and How
•
105
Nemotron-Personas: Improve AI Training With the First Synthetic Personas Dataset Aligned to Real-World Distributions
•
25
How I Trained Action Chunking Transformer (ACT) on SO-101: My Journey, Gotchas, and Lessons
•
61
How We Use Claude Code Skills to Run 1,000+ ML Experiments a Day
•
56
Building Autonomous Vehicles That Reason with the NVIDIA Alpamayo Open Ecosystem
•
22
Granite 4.0 1B Speech: Compact, Multilingual, and Built for the Edge
•
12
**Canada Must Not Turn AI Chatbots Into a New Surveillance Frontier**
•
3