Community Blog & Articles

Community Articles

Fine-tune video and image models at scale with NVIDIA NeMo Automodel and 🤗 Diffusers

Newer Models, Same Advantage

Security incident disclosure — July 2026

What building Shippy taught us about building agents

Model Routing Is Simple. Until It Isn’t.

Welcome Inkling by Thinking Machines

Introducing Real World VoiceEQ: Measuring the human quality of voice AI

Profiling in PyTorch (Part 3): Attention is all you profile

Native-speed vLLM transformers modeling backend

From Hugging Face to Amazon SageMaker Studio in one click

Hugging Face Models on Foundry Managed Compute

Run AI workloads on any cloud, store on Hugging Face: zero-egress storage with SkyPilot

LeRobot v0.6.0: Imagine, Evaluate, Improve

PRX Part 4: Our Data Strategy

NEW Articles from Team or Enterprise organizations will get promoted to the main section.

Community Blog & Articles

NVIDIA Nemotron 3 Embed Ranks #1 Overall on RTEB, Advancing Agentic Retrieval

Kimi K3 Model Overview: 2.8T Parameters, MXFP4 Quantization, and What the Open Weights Mean for the Community

J-Space: Yet Another LLM Mind Reader?

Aether-7B-5Attn: A 100% Open-Source Sovereign Foundation Model — and a Controlled Experiment in Heterogeneous Attention

One Adapter, Both Modalities: Field Notes from Building and Serving a Multimodal Reranker

KV Caching Explained: Optimizing Transformer Inference Efficiency

Deploy GLM-5.2-FP8 as your open, frontier-level agent

Uncensor any LLM with abliteration

Data for Agents

The state-of-the-art in open-source AI for Swiss legal tasks

The Best Open Source and Open-Weight LLM Models to Run Locally in 2026

Giving AI Agents 3D Bodies, Real Jobs, and Wallets on three.ws

When will language models be good enough?

Distillation in 2026 (so far): which frontier models use it and how

VKUE: No GPU? Runs Anyway — a 34.7B Reasoner on a Laptop and on Bare CPU

makeMoE: Implement a Sparse Mixture of Experts Language Model from Scratch

Code a simple RAG from scratch

Small Language Models (SLM): A Comprehensive Overview

Arabic LLM Models

How I Trained Action Chunking Transformer (ACT) on SO-101: My Journey, Gotchas, and Lessons

Fine-tune video and image models at scale with NVIDIA NeMo Automodel and 🤗 Diffusers

Newer Models, Same Advantage

Security incident disclosure — July 2026

What building Shippy taught us about building agents

Model Routing Is Simple. Until It Isn’t.

Welcome Inkling by Thinking Machines

Introducing Real World VoiceEQ: Measuring the human quality of voice AI

Profiling in PyTorch (Part 3): Attention is all you profile

Native-speed vLLM transformers modeling backend

From Hugging Face to Amazon SageMaker Studio in one click

Hugging Face Models on Foundry Managed Compute

Run AI workloads on any cloud, store on Hugging Face: zero-egress storage with SkyPilot

LeRobot v0.6.0: Imagine, Evaluate, Improve

PRX Part 4: Our Data Strategy

NVIDIA Nemotron 3 Embed Ranks #1 Overall on RTEB, Advancing Agentic Retrieval

Kimi K3 Model Overview: 2.8T Parameters, MXFP4 Quantization, and What the Open Weights Mean for the Community

J-Space: Yet Another LLM Mind Reader?

Aether-7B-5Attn: A 100% Open-Source Sovereign Foundation Model — and a Controlled Experiment in Heterogeneous Attention

One Adapter, Both Modalities: Field Notes from Building and Serving a Multimodal Reranker

KV Caching Explained: Optimizing Transformer Inference Efficiency

Deploy GLM-5.2-FP8 as your open, frontier-level agent

Uncensor any LLM with abliteration

Data for Agents

The state-of-the-art in open-source AI for Swiss legal tasks

The Best Open Source and Open-Weight LLM Models to Run Locally in 2026

Giving AI Agents 3D Bodies, Real Jobs, and Wallets on three.ws

When will language models be good enough?

Distillation in 2026 (so far): which frontier models use it and how

VKUE: No GPU? Runs Anyway — a 34.7B Reasoner on a Laptop and on Bare CPU

makeMoE: Implement a Sparse Mixture of Experts Language Model from Scratch

Code a simple RAG from scratch

Small Language Models (SLM): A Comprehensive Overview

Arabic LLM Models

How I Trained Action Chunking Transformer (ACT) on SO-101: My Journey, Gotchas, and Lessons