08:11 Tutorials2 months ago OUI-1: Builds UI Screens Instantly Locally Fahd Mirza installs and demos OUI-1, an unusual AI model that generates complete user interface screens using diffusion rather than a... 0 comments 4.5K views
01:28:12 Deep Dives3 months ago Deep dive on LLM Inference at Scale — Harshul Jain, Audible & Tanmay Sah, Independent AI Researcher Harshul Jain, senior software engineer at Audible and author of an open-source LLM inference handbook, teams up with AI researcher Ta... 0 comments 1.4K views
12:20 Benchmarks3 months ago K2 Horizon: 0.9B, 7B, and 32B Tested Locally, Real Results The Institute of Foundation Models — the AI research arm of MBZUAI, a university in Abu Dhabi with satellite labs in Paris and Silico... 0 comments 1.3K views
08:23 Coding & Builds3 months ago Thomson Reuters Built Their Own AI Lawyer: Run Thomson-1 Locally Fahd Mirza puts Thomson Reuters' newly released Thomson-1 Small model through a structured evaluation to determine whether an open-we... 0 comments 3.3K views
08:35 Tutorials3 months ago Install Pipecat PhoneLLM Locally for Free Voice AI Agent Fahd Mirza walks through a complete local installation and live evaluation of PhoneLLM, the fine-tuned voice agent model released by... 0 comments 5.4K views
55:18 Interviews3 months ago Build a $5,000 AI Datacenter at Home, Here’s How David Ondrej interviews Ahmed, a prominent open-source AI advocate, on the case for owning your AI infrastructure rather than dependi... 0 comments 11.7K views
21:48 Deep Dives3 months ago KV Cache-Aware Routing and P/D Disaggregation on Kubernetes — Yuchen Fama & Ashish Kamra, Red Hat At the AI Engineer conference, Red Hat's Yuchen Fama (vLLM contributor and product manager) and Ashish Kamra (senior manager of perfo... 0 comments 3.6K views
08:14 Reviews & Comparisons3 months ago SIE vs vLLM — Stop Using the Wrong Inference Engine Fahd Mirza runs a live head-to-head comparison of two LLM inference engines — Superlinked Inference Engine (SIE) and vLLM — directly... 0 comments 2.7K views
11:53 Benchmarks3 months ago Granite 4.2 (3B vs 8B): IBM’s New Reasoning Models, Tested Locally Fahd Mirza runs IBM's newly released Granite 4.2 model family through a practical local benchmark, testing both the 3B and 8B paramet... 0 comments 2.7K views
10:30 Benchmarks3 months ago Ornith-1.5-9B: Great on Paper, Struggled in My Tests Locally Fahd Mirza tests the Ornith 1.5 9B model — the smallest and densest member of the Ornith 1.5 family — on a single NVIDIA A100 with 80... 0 comments 1.7K views