Community Blog & Articles

Community Articles

The Fast Gemma Challenge: our verified-SOTA recipe, in full

Training a coding agent using the OpenCode harness in remote HF sandboxes with TRL and OpenEnv

Lattice: an 8 MB static retriever that embeds Wikipedia in 7 minutes

The OlmoEarth Platform: Geospatial inference at planetary scale

mDenseOn with the mLateOn: Open Multilingual, Long-Context, and Code Retrieval Models

LFM2.5-Encoders for Fast Long-Context Inference on CPU

超越表层对齐：信念是通往深层对齐的新入口

Alibaba-VELLDEPTH

Model Genome: Fingerprinting Whether an LLM Was Trained From Scratch or Derived

about 3 hours ago

Code a simple RAG from scratch

Uncensor any LLM with abliteration

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

Language Identification for 42 Indian Languages: Opening New Frontiers in Indic Speech AI

Rebuilding Among AIs from Six Log Files

about 23 hours ago

FLUX 3 Model Overview: Multimodal Flow Models for Image, Video, Audio, and Action Prediction

Bekko Embedding: how small can a multilingual retrieval model be?

jina-reranker-v3.5: Faster Listwise Reranking with Hybrid Attention and Self-Distillation

Optimum Intel v2.1.0

KV Caching Explained: Optimizing Transformer Inference Efficiency

Using OCR models with llama.cpp

ECMWF's AI forecasting model is open source: now let's make it easy to run.

hugging-science

TutorMoments: Do AI tutors know when to help and when to hold back?

llmsinference-providersbaseten

Baseten on Hugging Face Inference Providers 🔥

+4

Deploy local agents everywhere with LFM2.5-2.6B

GPU Management: Why Idle GPUs Are the New Grounded Aircraft

NVIDIA Cosmos-H-Dreams: Bringing Real-Time Generative Simulation to Surgical Robotics

Anatomy of a Frontier Lab Agent Intrusion: A Technical Timeline of the July 2026 Incident

guidediffusersquantization

Bringing Nunchaku 4-bit Diffusion Inference to Diffusers

roboticsaicommunity

Grabette: an open system to record robot-manipulation data

+2

Newer Models, Same Advantage

Security incident disclosure — July 2026

Model Routing Is Simple. Until It Isn’t.

announcementmultimodaltransformers

Welcome Inkling by Thinking Machines

+1

audiospeechbenchmark

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

+9

torchprofileflash

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

Community Articles

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

The Fast Gemma Challenge: our verified-SOTA recipe, in full

Training a coding agent using the OpenCode harness in remote HF sandboxes with TRL and OpenEnv

Lattice: an 8 MB static retriever that embeds Wikipedia in 7 minutes

The OlmoEarth Platform: Geospatial inference at planetary scale

mDenseOn with the mLateOn: Open Multilingual, Long-Context, and Code Retrieval Models

LFM2.5-Encoders for Fast Long-Context Inference on CPU

超越表层对齐：信念是通往深层对齐的新入口

Alibaba-VELLDEPTH

Model Genome: Fingerprinting Whether an LLM Was Trained From Scratch or Derived

about 3 hours ago

Code a simple RAG from scratch

Uncensor any LLM with abliteration

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

Language Identification for 42 Indian Languages: Opening New Frontiers in Indic Speech AI

Rebuilding Among AIs from Six Log Files

about 23 hours ago

FLUX 3 Model Overview: Multimodal Flow Models for Image, Video, Audio, and Action Prediction

Bekko Embedding: how small can a multilingual retrieval model be?

jina-reranker-v3.5: Faster Listwise Reranking with Hybrid Attention and Self-Distillation

Optimum Intel v2.1.0

KV Caching Explained: Optimizing Transformer Inference Efficiency

Using OCR models with llama.cpp

ECMWF's AI forecasting model is open source: now let's make it easy to run.

hugging-science

View all articles