06:49
Nanowhale-100m: Fascinating Implemention of DeepSeek-V4 Architecture
Fahd Mirza walks through Nanowhale-100M, a 110 million parameter language model built entirely from scratch—no borrowed weights—that...
Sort by: Newest Items
There are 178 items in this page
08:15
MisoTTS – Most Emotive Voice Model in the World – Really?
Fahd Mirza puts MesoTTS 8B — a new open-weights text-to-speech model built on the Sesame CSM architecture — through a hands-on instal...
13:26
Gemma4 12B vs Qwen3.6 27B — The Veteran vs The Newcomer
Fahd Mirza runs a structured head-to-head comparison of Gemma 4 12B and Qwen 3.6 27B on the same Nvidia H100 80GB VRAM system, testin...
12:13
Gemma 4 12B – Google’s Unified Multimodal Model Running Locally
Fahd Mirza walks through a complete local installation and multi-modal evaluation of Gemma 4 12B, Google's newest open-weight model,...
11:11
Run NVIDIA Cosmos 3 Locally: Frontier Model for Physical AI
NVIDIA Cosmos 3 is a world foundation model built specifically for physical AI — a category targeting robotics and autonomous vehicle...
08:12
LocateAnything: NVIDIA’s New AI Sees EVERYTHING: Run Locally
NVIDIA's LocateAnything is a 3-billion-parameter vision-language model that goes beyond standard image classification to precisely lo...
13:02
MiniMax M3: Frontier Coding, 1M Context, Native Multimodality – Thorough Testing
Fahd Mirza puts MiniMax M3 through a hands-on evaluation, opening with a striking demonstration: a single prompt produces a fully sel...
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...
10:07
Dolphin X1 Trinity Nano: The Model That Never Says No: Run and Test Locally
Fahd Mirza walks through the local deployment and testing of Dolphin X1 Trinity Nano, the first model trained entirely within a custo...
08:38
HRM-Text-1B: A 1B Model That Beats 7B Models for $1,500: Test Locally
HRM-Text-1B is a 1 billion parameter pre-trained language model that claims to match or outperform models in the 2–7 billion paramete...