11:55 Coding & Dev Tools2 weeks ago Run Muse Glimmer 30B Locally: Open Agentic Model Fahd Mirza walks through installing and testing Muse Glimmer 30B — described as Meta's first open-weights release from its superintel... 0 comments 1.5K views
19:50 Business & Strategy2 weeks ago Taking Reinforcement Learning Cross Datacenter — Nan Jiang, Modal At an AI Engineer conference, Nan Jiang from Modal presents a technical architecture for running reinforcement learning post-training... 0 comments 248 views
46:18 Interviews3 weeks ago How Open Source Became AI’s Backbone | Inferact with a16z In this a16z-hosted conversation, Simon Mo — co-founder of Infact and lead maintainer of vLLM, the open-source inference engine now r... 0 comments 1K views
09:48 Coding & Dev Tools3 weeks ago Mistral Shieldstral, Content Moderation Changed in Plain English Fahd Mirza walks through a local installation and live evaluation of Mistral's newly released Shieldstral — a 3-billion-parameter ope... 0 comments 687 views
12:23 Coding & Dev Tools4 weeks ago Microsoft Fara1.5 27B: Local Install + Real Browser Automation Demo Fahd Mirza installs and live-tests Microsoft's newly released Fara 1.5 27B, a vision-only browser automation model that controls a we... 0 comments 3.3K views
08:12 Tutorials4 weeks ago How to Run Kimi K3 Locally (3 Ways) Fahd Mirza delivers an honest, hardware-grounded assessment of running Kimi K3 — Moonshot AI's 2.8-trillion-parameter, 104-billion-ac... 0 comments 3.1K views
09:16 Coding & Dev Tools4 weeks ago DeepSeek V4 Flash Fully Local — 32 tok/s on a Single Chip Fahd Mirza demonstrates running DeepSeek V4 Flash, a 284-billion parameter mixture-of-experts model, entirely on a single AMD Ryzen A... 0 comments 5.2K views
09:20 Coding & Dev Tools1 month ago Nanbeige4.2 – 3B Model That Beats 9B Models | Local Install + Real App Test Fahd Mirza tests Nanbeige 4.2, the second release from Nan Beach and a 3-billion-parameter model built on a "looped transformer" arch... 0 comments 1.5K views
08:12 Tutorials1 month ago Gemma 4 Just Got a Massive Update (Tested Live Locally) Fahd Mirza puts Gemma 4's latest patch update under the microscope in a live session running on an Nvidia H100 with vLLM on a fresh U... 0 comments 4.2K views
49:44 Interviews1 month ago The AI Memory Problem: Why Long Context Isn’t Enough — Dan Biderman, Engram Co-founder & CEO Dan Biderman, co-founder and CEO of Engram — the AI memory startup that raised a $98 million seed round — joins the Latent Space podc... 0 comments 726 views