13:21
Gemma 4 E2B + Hermes Agent + vLLM: Multimodal AI Stack Locally for Free
Fahd Mirza demonstrates a full local stack for running Google's Gemma 4 E2B instruction-tuned model through the Hermes agentic framew...
Sort by: Newest Items
There are 76 items in this page
16:58
Gemma 4 E4B + Ollama + OpenClaw — Run It Locally for Free
This video from Fahd Mirza walks through running Google's Gemma 4 E4B model entirely locally using Ollama and OpenClaw — at no cost b...
19:08
Gemma 4 Dances Into the Future – Google’s Most Powerful 31B Open Model Installed Locally
Google DeepMind's Gemma 4 is a new open-source model family released in April 2026, covering four sizes: E2B, E4B, a 26B mixture-of-e...
17:04
GLM 5.1 with OpenClaw: Full Setup Guide with Testing and Whinging
Zhipu AI has released GLM 5.1, a coding-focused large language model that marks a significant departure from the team's previously fr...
10:57
Cohere Transcribe: Local ASR Model – Audio In, Text Out in 14 Languages
Cohere has quietly released a new automatic speech recognition model called Cohere Transcribe, and in this video Fahd Mirza walks thr...
08:07
MolmoWeb – Fully Open Multimodal Web Agents – Control Browser Locally
MolmoWeb is a fully open-source visual web agent released by the Allen Institute for AI (AI2) that autonomously controls a real web b...
11:46
Hermes-Agent + Qwen3.5 + LM Studio: Self-Improving AI Agent Locally
Fahd Mirza demonstrates a complete local setup for running Hermes Agent using LM Studio as the model server, using an Ubuntu machine...
Hermes Agent + Ollama + Telegram – Local Easy Setup Guide
Fahd Mirza walks through a complete local installation of Hermes, the new agent released by NovaSky Research (the lab behind several...
08:57
DeepSeek Did It. Now LongCat Just Raised the Bar with Flash Prover
AI researcher Fahd Mirza puts LongCat Flash Prover through its paces in this hands-on review, covering one of the most capable open-s...
10:25
MiniMax M2.7 + OpenClaw — AI That Helped Build Itself with Token Plan
Fahd Mirza walks through integrating MiniMax M2.7 — a newly released model distinguished by having participated in its own training p...