14:35
Google QAT vs Unsloth Q4_0 – Which Gemma 4 12B Quantization Is Better?
Fahd Mirza runs a controlled comparison between two 4-bit quantized versions of Google's Gemma 4 12B model: Google's own QAT (quantiz...
Sort by: Newest Items
There are 135 items in this page
13:43
Gemma4 12B in Quantization-Aware Training (QAT) with Ollama – Full Testing
Google's Gemma 4 12B model now has Quantization-Aware Training (QAT) checkpoints, and Fahd Mirza puts them through a full workout in...
09:08
Hermes Desktop + Ollama: Run a Self-Improving AI Agent on Your Own Server
Fahd Mirza walks through the installation and configuration of Hermes agent desktop, the newly released GUI for the Hermes agent fram...
08:13
Your AI Agent Is Leaking Your API Keys (Fix It With Free Agent-Vault)
AI agents that read and write files on a developer's behalf — frameworks like OpenClaw and others — silently pass the full contents o...
12:15
Claude Code + LM Studio: FREE Unlimited AI Agents (Don’t Pay $200/month)
This tutorial walks through connecting Claude Code and Claude Desktop to a completely local LLM backend using LM Studio, eliminating...
08:32
WeasyPrint with Ollama Tutorial: HTML to PDF with AI Integration
Fahd Mirza walks through a complete integration of WeasyPrint — a lightweight Python-based HTML-to-PDF rendering engine — with Ollama...
32:57
Unsloth Studio is insane… fine-tune any AI model locally
Unsloth Studio is a free, open-source desktop application that brings LLM fine-tuning to consumer hardware — and this video by David...
14:33
Running Local AI on AMD
Sam Witteveen takes a hands-on look at running local AI on an AMD workstation equipped with a Ryzen Threadripper 9980X processor and...
12:50
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...
11:11
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...