Two Years of Local AI on a Laptop: When Open Models Outpaced Moore's Law
mishig
• • 20Community Blog & Articles
Community Articles
view all
Granite Embedding Multilingual R2: Open Apache 2.0 Multilingual Embeddings with 32K Context — Best Sub-100M Retrieval Quality
19
May 14, 2026 
transformerspytorchoptimization
Unlocking asynchronicity in continuous batching
35
May 14, 2026 
Building Blocks for Foundation Model Training and Inference on AWS
20
May 11, 2026 
EMO: Pretraining mixture of experts for emergent modularity
33
May 8, 2026 vLLM V0 to V1: Correctness Before Corrections in RL
8
May 6, 2026 
audiospeechleaderboard
Adding Benchmaxxer Repellant to the Open ASR Leaderboard
- +7
15
May 6, 2026 Granite 4.1 LLMs: How They’re Built
70
April 29, 2026 
llmsinference-providersdeepinfra
DeepInfra on Hugging Face Inference Providers 🔥
- +4
9
April 29, 2026 Introducing NVIDIA Nemotron 3 Nano Omni: Long-Context Multimodal Intelligence for Documents, Audio and Video Agents
55
April 28, 2026 
openaiprivacy-filterweb-apps
How to build scalable web apps with OpenAI's Privacy Filter
8
April 27, 2026 
llmmoelong-context
DeepSeek-V4: a million-token context that agents can actually use
44
April 24, 2026 
guidetransformers.jsjavascript
How to Use Transformers.js in a Chrome Extension
36
April 23, 2026 
QIMMA قِمّة ⛰: A Quality-First Arabic LLM Leaderboard
12
April 21, 2026 
cybersecurityopen-sourcecommunity
AI and the Future of Cybersecurity: Why Openness Matters
38
April 21, 2026 NEW Articles from Team or Enterprise organizations will get promoted to the main section.
Two Years of Local AI on a Laptop: When Open Models Outpaced Moore's Law
mishig
• • 20Training-Free Reasoning at 88.89% on GPQA Diamond: How Darwin Family Hit Frontier Scores Without a Single Gradient Step
FINAL-Bench
• • 12Vividh-ASR: Diagnosing and Fixing Studio-Bias in Whisper for Indic Languages
adalat-ai
• • 11"OncoAgent: A Dual-Tier Multi-Agent Framework for Privacy-Preserving Oncology Clinical Decision Support"
lablab-ai-amd-developer-hackathon
• • 9KV Caching Explained: Optimizing Transformer Inference Efficiency
not-lain
• • 329NEO-unify: Building Native Multimodal Unified Models End to End
sensenova
• • 161How to Comply with SOC 2 and ISO 27001 with Hugging Face: A Practical Guide to AI Model Supply Chain Governance
jeffboudier
• • 4From GRPO to DAPO and GSPO: What, Why, and How
NormalUhr
• • 118A Guide to Reinforcement Learning Post-Training for LLMs: PPO, DPO, GRPO, and Beyond
karina-zadorozhny
• • 18QVAC MedPsy: State-of-the-Art Medical and Healthcare Language Models for Edge Devices
qvac
• • 15Pallas for people who know JAX but not kernels yet
ariG23498
• • 21Introducing the agentic robotics appstore for 10,000 Reachy Minis
clem
• • 34CyberSecQwen-4B: Why Defensive Cyber Needs Small, Specialized, Locally-Runnable Models
lablab-ai-amd-developer-hackathon
• • 7Safety Evals Should Project Test-Time Compute
Cerru02
• • 3You do the work. Big Tech takes the model.
urroxyz
• • 3Self Evolving is the Endgame or final destiny
rajkumarrawal
• • 3Uncensor any LLM with abliteration
mlabonne
• • 852makeMoE: Implement a Sparse Mixture of Experts Language Model from Scratch
AviSoori1x
• • 121Code a simple RAG from scratch
ngxson
• • 333Mastering Tensor Dimensions in Transformers
not-lain
• • 172