Nemotron 3 Nano \- A new Standard for Efficient, Open, and Intelligent Agentic Models
•
92
Community Blog & Articles
Community Articles
view all
tokenizerstransformersopen-source
Tokenization in Transformers v5: Simpler, Clearer, and More Modular
- +2
55
December 18, 2025
The Open Evaluation Standard: Benchmarking NVIDIA Nemotron 3 Nano with NeMo Evaluator
30
December 17, 2025
CUGA on Hugging Face: Democratizing Configurable AI Agents
46
December 15, 2025
New in llama.cpp: Model Management
89
December 11, 2025
llmfine-tuningopen-source
Codex is Open Sourcing AI models
44
December 11, 2025
Apriel-1.6-15b-Thinker: Cost-efficient Frontier Multimodal Performance
78
December 9, 2025
swifthubopen-source
Introducing swift-huggingface: The Complete Swift Client for Hugging Face
31
December 5, 2025
llmreasoningagents
DeepMath: A lightweight math reasoning Agent with smolagents
30
December 4, 2025
llmfine-tuningopen-source
Hot
We Got Claude to Fine-Tune an Open Source LLM
521
December 4, 2025
transformersv5community
Hot
Transformers v5: Simple model definitions powering the AI ecosystem
246
December 1, 2025
diffusersfluxquantization
Diffusers welcomes FLUX-2
- +4
164
November 25, 2025
transformerspytorchoptimization
Hot
Continuous batching from first principles
281
November 25, 2025
Building Deep Research: How we Achieved State of the Art
28
November 24, 2025
OVHcloud on Hugging Face Inference Providers 🔥
73
November 24, 2025
NEW
Articles from
Team
or
Enterprise organizations will get promoted to the main section.
Nemotron 3 Nano \- A new Standard for Efficient, Open, and Intelligent Agentic Models
•
92
Qwen-Image-i2L: Training Strategies for Image-to-LoRA Generation
•
33
EuroLLM-22B
•
32
Shadow AI - Where are the CIOs?
•
29
LLM based TTS models
•
28
Spinning Up a CPU-Only Micro-LLM with LoRA for Literary Style
•
21
Gotchas in Tokenizer Behavior Every Developer Should Know
•
62
How We Use Claude Code Skills to Run 1,000+ ML Experiments a Day
•
45
Why You Should Care About Partial Differential Equations (PDEs)
•
30
Phare LLM benchmark V2: Reasoning models don't guarantee better security
•
9
Announcing LiteCoder-Terminal: Lightweight Terminal Agents with <1k Synthesized Trajectories
•
9
Make and publish your Reachy Mini App
•
20
MiniGuard-v0.1: Prem's Guardrail Model Redefining the Pareto Frontier
•
21
Uncensor any LLM with abliteration
•
740
cua-bench: A Framework for Benchmarking, Training Data, and RL Environments for Computer-Use Agents
•
6
Open Collaboration in Action: Inside the Open Safeguard Hackathon
•
6
KV Caching Explained: Optimizing Transformer Inference Efficiency
•
199
How to make NeuTTS-air generate over 200 seconds of audio in a single second.
•
17
Code a simple RAG from scratch
•
268
🦸🏻#14: What Is MCP, and Why Is Everyone – Suddenly!– Talking About It?
•
348