08:41 Tutorials5 months ago Microsoft FastContext: The 4B Bug Hunter: Run Locally Microsoft's FastContext is a specialized 4-billion-parameter model designed to eliminate a costly inefficiency in AI coding agents: r... 0 comments 2.5K views
09:40 Benchmarks5 months ago DFlash Just Got Faster: 4x Speed with 160 tok/s Locally Fahd Mirza benchmarks DFlash with SGLang's new SpecV2 overlapping scheduler on an NVIDIA H100 80GB GPU, demonstrating a 4.3x throughp... 0 comments 2.2K views
12:46 Coding & Builds5 months ago VibeThinker-3B: 3B Model That Challenges Claude Opus? Test Locally Fahd Mirza installs and tests VibeThinker-3B — a reasoning model released by Weibo, the Chinese social media giant — directly on an N... 0 comments 2.8K views
11:01 Tutorials6 months ago Higgs Audio v3 TTS: This Model Does Not Read, It Talks in Your Language Fahd Mirza demonstrates Higgs Audio V3, a multilingual text-to-speech model from Boson AI, running entirely locally on an Nvidia RTX... 0 comments 1.3K views
12:27 Coding & Builds6 months ago Nemotron 3 Ultra – NVIDIA’s Most Powerful Open Model – Long Running Agents NVIDIA has released Nemotron Ultra, its largest open model to date at 550 billion total parameters—with only 55 billion active at inf... 0 comments 1.8K views
12:40 Deep Dives6 months ago What Lies Beneath the API — Benjamin Cowen, Modal Benjamin Cowen, a forward-deployed machine learning engineer at Modal, delivers a conference talk examining one of the most consequen... 0 comments 554 views
09:39 Coding & Builds6 months ago Step 3.7 Flash – 198B Open Source Model That Does Everything; Does it Really? Step 3.7 Flash is a 198 billion parameter sparse mixture-of-experts model from Step One, activating only 11 billion parameters per to... 0 comments 1.9K views
01:07:19 Deep Dives6 months ago Inference, Diffusion, World Models, and More | YC Paper Club Y Combinator's inaugural Paper Club brought together roughly 100 selected founders and researchers at Pioneer in Woodside, CA — drawi... 0 comments 8.8K views
10:10 Tutorials6 months ago Intern-S2-Preview FP8: 35B Scientific Multimodal Model Running Locally InternLM's latest release, Intern-S2-Preview, is a 35-billion-parameter scientific multimodal model that takes a different approach t... 0 comments 1.3K views
33:45 Coding & Builds6 months ago AI Dev 26 x SF | Eda Zhou & Mahdi Ghodsi: Building Personal AI Agents with Open Source Models At the AI Dev 26 conference in San Francisco, AMD engineers Eda Zhou and Mahdi Ghodsi lead a hands-on workshop teaching attendees how... 0 comments 742 views