08:13
Mistral Small 4 is Here: One Model That Does it All
Mistral AI's Mistral Small 4 is a newly released mixture-of-experts model with 119 billion total parameters — only 6.5 billion of whi...
Sort by: Newest Items
There are 313 items in this page
08:15
Qwen3.5 + Claude Code: Run a Free Local AI Coding Agent
Fahd Mirza walks through building a fully offline, private AI coding agent by combining Anthropic's Claude Code with the Qwen3.5 4-bi...
09:51
Tri-21B Think: Breaking US-China Duopoly in AI Dominance: Run Locally
Fahd Mirza takes a hands-on look at Tri-21B Think, an open-weight reasoning model from Trillion Labs, a South Korean AI startup. The...
27:28
Claude JUST became AWARE
Anthropic has published findings from an evaluation of Claude Opus 4.6 documenting what researchers call situational awareness—a mode...
12:49
Is LTX 2.3 the Ultimate Open-Source Video AI?|Run LTX 2.3 on Low VRAM|Three comfyUI workflow
LTX 2.3 from Lightricks is the latest milestone in open-source video generation, upgrading from 19B to 22B parameters with improved v...
09:08
pplx-embed: Embedding Models for Web-Scale Retrieval: Run Locally
Fahd Mirza installs and tests pplx-embed, Perplexity AI's new 600 million parameter multilingual text embedding model built on top of...
08:05
LLMfit – Stop Guessing Which AI Models Fit Your GPU or CPU Locally
Fahd Mirza introduces LLMfit, a command-line tool designed to eliminate the guesswork involved in selecting local language models for...
19:13
Fine-Tune Qwen3.5 0.8B Locally On Your Own Dataset – Full Easy Guide
Fahd Mirza walks through a complete, reproducible guide to fine-tuning Qwen 3.5 0.8B locally using the Unsloth library and LoRA (Low...
10:49
Liquid AI LFM2-24B: Local Install, Test & Honest Review
Fahd Mirza installs and tests Liquid AI's newly released LFM2-24B mixture-of-experts model locally using vLLM on an Nvidia H100 with...
11:29
Stop Using Qwen! Fire-Red-Edit is the New King|Master ComfyUI Image Editing with Fire-Red-Edit
Fire Red Edit is an open-source image editing model claiming superiority over Qwen Image Edit in accuracy, subject consistency, and i...