Inside three.ws: The Open-Source Stack That Gives AI Agents a Body, a Brain, a Wallet, and a Job
three-ws
• • 41Community Blog & Articles
Community Articles
view all
announcementmultimodaltransformers
Welcome Inkling by Thinking Machines
- +1
165
July 15, 2026 
audiospeechbenchmark
Introducing Real World VoiceEQ: Measuring the human quality of voice AI
- +9
33
July 15, 2026 
torchprofileflash
Profiling in PyTorch (Part 3): Attention is all you profile
48
July 10, 2026 
vllmtransformersinference
Native-speed vLLM transformers modeling backend
74
July 8, 2026 
From Hugging Face to Amazon SageMaker Studio in one click
21
July 7, 2026 
Hugging Face Models on Foundry Managed Compute
20
July 7, 2026 
guidepartnershipsopen-source-collab
Run AI workloads on any cloud, store on Hugging Face: zero-egress storage with SkyPilot
- +1
32
July 7, 2026 
lerobotrobotics
LeRobot v0.6.0: Imagine, Evaluate, Improve
- +5
84
July 7, 2026 
PRX Part 4: Our Data Strategy
7
July 6, 2026 
kernelshuboptimization
🤗 Kernels: Major Updates
35
July 6, 2026 
partnershipsaudioopen-source-collab
Hugging Face and Cerebras bring Gemma 4 to real-time voice AI
100
July 1, 2026 
ScarfBench: Benchmarking AI Agents for Enterprise Java Framework Migration
26
June 30, 2026 
Why Specialization Is Inevitable
18
June 30, 2026 
evaluationcommunityleaderboard
Featuring Every Eval Ever Results on Hugging Face Model Pages
- +3
52
June 30, 2026 NEW Articles from Team or Enterprise organizations will get promoted to the main section.
Inside three.ws: The Open-Source Stack That Gives AI Agents a Body, a Brain, a Wallet, and a Job
three-ws
• • 41Extremely Fast and Accurate Transcription with Granite Speech 5.0 Turbo CTC
ibm-granite
• • 30Writing Down the Line Between Luck and Skill
FINAL-Bench
• • 14Modern LLMs: What the FLIP is an Engram!?
Blackroot
• • 10Introducing the EdgeFirst Model Zoo
EdgeFirst
• • 8Uncensor any LLM with abliteration
mlabonne
• • 905Agentic RL: Token-In, Token-Out Done Right
huggingface
• • 30We changed one line and the benchmark score moved 0.21 AUROC
FINAL-Bench
• • 13TAVR: Generate Your Talking Avatar from Video Reference
HeyGenAI
• • 4TransVLM: Detecting Any Shot Transition with Vision-Language Models
HeyGenAI
• • 4Small Language Models (SLM): A Comprehensive Overview
jjokah
• • 174NEO-unify: Building Native Multimodal Unified Models End to End
sensenova
• • 179The Best Open Source and Open-Weight LLM Models to Run Locally in 2026
daya-shankar
• • 19Extreme Overtraining in Tiny Language Models
Banaxi-Tech
• • 12EgoSuite-Open100K: 100,000 hours of egocentric human data for Physical AI
LightwheelAI
• • 3Intel GPU AI Skills
kushal-mittal
• • 3Stop Abusing Git for ML Data: The Architect’s Guide to AI Storage
prpatel
• • 3ColPali: Efficient Document Retrieval with Vision Language Models 👀
manu
• • 329The Large Language Model Course
mlabonne
• • 233How I Trained Action Chunking Transformer (ACT) on SO-101: My Journey, Gotchas, and Lessons
sherryxychen
• • 80