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 95 items in this page
18:32
Gemma 4 Has Landed!
Google has released Gemma 4, a family of four open-weight models that represents a meaningful inflection point in the open-source AI...
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...
10:27
Voxtral 4B TTS 2603: Installation + 9-Language Demo (Open-Source ElevenLabs Alternative)
Fahd Mirza walks through a complete local installation of Mistral's newly released Voxtral 4B—a 4-billion-parameter open-weight text-...
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...
08:33
Qwen3 Speculator Eagle: Red Hat Made Qwen3-8B 6x Faster: Full Hands-on Guide
Red Hat has quietly entered the AI inference space with a significant technical contribution: a speculative decoding model that makes...
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...
15:10
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...
09:20
Run Dots.mOCR Locally — OCR, LaTeX, SVG From Any Image
dots.m OCR is a 1.7-billion-parameter vision-language model from Red Note — the Chinese lifestyle platform also known as Little Red B...
08:25
MiniCPM-SALA: Model That Makes 1M Token Context Actually Work
Fahd Mirza digs into MiniCPM-SALA, a new pre-trained model from the MiniCPM lab that introduces a hybrid attention architecture aimed...