08:53 Coding & Dev Tools3 months ago LFM2.5-8B-A1B: Local Agentic AI with Multilingual Support Tested LFM2.5-8B-A1B is Liquid AI's latest open-weight model — an 8.3 billion parameter mixture-of-experts architecture that activates only... 0 comments 1.7K views
11:05 Tutorials3 months ago Bonsai Image: The World’s First 1-bit Image Generator — Running Locally Prism ML has released Bonsai Image 4B, billed as the world's first 1-bit image generation model, and Fahd Mirza runs it locally in th... 0 comments 4.1K views
20:40 Tutorials3 months ago Stable Audio 3: Created Music From 20+ Countries Locally Fahd Mirza walks through a complete local installation and stress test of Stable Audio 3, Stability AI's latest open-weights audio ge... 0 comments 687 views
10:06 Coding & Dev Tools3 months ago DFlash Leaves Qwen Territory – Gemma 4 31B Now Runs 5x Faster with Speculative Decoding Fahd Mirza demonstrates the first end-to-end deployment of Llama Box DFlash with Google's Gemma 4 31B model, following the merge of P... 0 comments 3.5K views
12:50 Tutorials3 months ago AgentMemory + Hermes Agent + Ollama = AI Agent That Never Forgets | Fully Local Setup Fahd Mirza demonstrates a fully local setup that gives AI coding agents persistent memory across sessions, combining the AgentMemory... 0 comments 2.2K views
11:11 Tutorials3 months ago MiniCPM5-1B: New 1B King for Local AI – Full Demo Fahd Mirza walks through a complete local installation and live evaluation of MiniCPM 5 in its 1 billion parameter variant, released... 0 comments 2.9K views
20:49 Research & Benchmarks3 months ago Qwen3.7 Max vs Claude Opus 4.6 — Honest Head to Head Tech YouTuber Fahd Mirza runs a structured, three-part head-to-head between Alibaba's Qwen 3.7 Max and Anthropic's Claude Opus 4.6, t... 0 comments 1.6K views
12:06 Tutorials3 months ago Qwen3.7 Max + OpenClaw — Full Setup and Live Agent Test Fahd Mirza walks through a full, production-style setup of Qwen 3.7 Max — Alibaba's latest frontier model — running as a fully autono... 0 comments 1K views
09:45 Tutorials3 months ago Llama.cpp Just Got MTP – Qwen3.6 27B Runs 2x Faster Locally with Two Flags Multi-token prediction (MTP) support has officially merged into the mainline llama.cpp repository—not a fork or custom branch, but th... 0 comments 3K views
16:50 Tutorials3 months ago Run HiDream-O1-Image Locally with ComfyUI Fahd Mirza walks through the complete local installation of HiDream-O1, a newly released 8-billion-parameter image generation model f... 0 comments 1K views