Fahd Mirza Creator Profile

How Beads Fixes Claude Code's Memory Loss

Fahd Mirza January 5, 2026

Beads gives Claude Code persistent memory across sessions by automatically tracking issues, dependencies, and context—so your AI pair programmer never …

GLM Fumbles: Releases ASR Nano Model: Install and Run Locally

Fahd Mirza January 5, 2026

The Most OPEN 32B Model Ever Just Dropped – OLMo 3.1

Fahd Mirza January 5, 2026

Run Uncensored MiniMax M2.1 on CPU Locally

Fahd Mirza January 4, 2026

This video locally installs and tests MiniMax-M2.1-PRISM which exists as research and development experimentation in AI Safety research. 🔥 Get …

Gas Town: Why 99% of Developers Shouldn't Use This AI Tool

Fahd Mirza January 4, 2026

Gas Town orchestrates 20-30 AI coding agents simultaneously - but it's only for developers already juggling multiple Claude Code instances …

Luxical-One: An Unappreciated AI Niche Model: Full Hands-on Local Demo

Fahd Mirza January 3, 2026

This video locally installs Luxical-One which is a small lexical-dense text embedding model. 🔥 Get 50% Discount on any A6000 …

Tarka Embedding - Multilingual AI for Deep Contextual Semantics - Run on CPU

Fahd Mirza January 3, 2026

AutoGLM Phone 9B: An AI Phone Agent for Android: Full Hands-on Demo

Fahd Mirza January 3, 2026

llm-d: Distributed Inference Infrastructure for Large Language Models

Fahd Mirza January 3, 2026

This video introduces llm-d, a Kubernetes-native distributed inference serving stack providing well-lit paths for anyone to serve large AI models …

OpenAI's Circuit Sparsity: AI That Shows Its Work | Local Demo + Tutorial

Fahd Mirza January 2, 2026

This video locally installs and Tests OpenAI's new sparse AI model that reveal its internal reasoning, unlike traditional black-box neural …

Youtu-LLM from Tencent: A Pocket-Rocket for AI Agents: Full Local Guide

Fahd Mirza January 2, 2026

This video locally installs and tests Youtu-LLM is a new, small, yet powerful LLM. 🔥 Get 50% Discount on any …

How to Run GLM-TTS Locally – Voice Cloning and Streaming for Free

Fahd Mirza January 2, 2026

IQuest-Coder-V1: Another DeepSeek Moment? Beating Claude Opus 4.5?

Fahd Mirza January 1, 2026

This video locally installs and tests IQuest-Coder-V1 is a code model to advance autonomous software engineering and code intelligence. 🔥 …

Hunyuan MT 1.5: Open Source Translation Model - 33 Languages Demo

Fahd Mirza January 1, 2026

This video locally installs HY-MT1.5 7B model, supporting mutual translation across 33 languages and incorporating 5 ethnic and dialect variations. …

Continuous Thought Machines by Sakana: AI Actually THINKS Before It Answers

Fahd Mirza January 1, 2026

Devstral 2 Small is Here - An Agentic Coding Model with Vision - Local Demo

Fahd Mirza January 1, 2026

Mistral Vibe CLI Demo: Free AI Coding Assistant for Programming

Fahd Mirza January 1, 2026

Qwen-Image-2512 with ComfyUI: New Year, New AI

Fahd Mirza December 31, 2025

This video locally installs and tests Qwen-Image-2512 with ComfyUI, the December update of Qwen-Image’s text-to-image foundational model. 🔥 Get 50% …

GLM-4.6V Enters with a Bang: High-Performance AI for Images and Videos

Fahd Mirza December 31, 2025

Encoderfile: Package Transformer Models into Standalone Executables

Fahd Mirza December 31, 2025

This video installs and tests Encoderfile which packages transformer encoders. 🔥 Get 50% Discount on any A6000 or A5000 GPU …

TurkColBERT: A Late-Interaction Model for Turkish RAG: Full Local Demo

Fahd Mirza December 30, 2025

Hermes 4 is Here: Decentralized and Democratized AI on Solana

Fahd Mirza December 30, 2025

HY-Motion 1.0 | Text-to-Motion AI Model - Full Local Hands-on Guide

Fahd Mirza December 30, 2025

This video locally installs HY-Motion 1, which is used to generate skeleton-based 3D character animations from simple text prompts. 🔥 …

EmbedAnything - Local Embedding Pipeline for RAG - Full Hands-on Demo

Fahd Mirza December 30, 2025

This video installs EmbedAnyting, which is multimodal, and local embedding pipeline for local RAG. 🔥 Get 50% Discount on any …

Fahd Mirza

How Beads Fixes Claude Code's Memory Loss

GLM Fumbles: Releases ASR Nano Model: Install and Run Locally

The Most OPEN 32B Model Ever Just Dropped – OLMo 3.1

Run Uncensored MiniMax M2.1 on CPU Locally

Gas Town: Why 99% of Developers Shouldn't Use This AI Tool

Luxical-One: An Unappreciated AI Niche Model: Full Hands-on Local Demo

Tarka Embedding - Multilingual AI for Deep Contextual Semantics - Run on CPU

AutoGLM Phone 9B: An AI Phone Agent for Android: Full Hands-on Demo

llm-d: Distributed Inference Infrastructure for Large Language Models

OpenAI's Circuit Sparsity: AI That Shows Its Work | Local Demo + Tutorial

Youtu-LLM from Tencent: A Pocket-Rocket for AI Agents: Full Local Guide

How to Run GLM-TTS Locally – Voice Cloning and Streaming for Free

IQuest-Coder-V1: Another DeepSeek Moment? Beating Claude Opus 4.5?

Hunyuan MT 1.5: Open Source Translation Model - 33 Languages Demo

Continuous Thought Machines by Sakana: AI Actually THINKS Before It Answers

Devstral 2 Small is Here - An Agentic Coding Model with Vision - Local Demo

Mistral Vibe CLI Demo: Free AI Coding Assistant for Programming

Qwen-Image-2512 with ComfyUI: New Year, New AI

GLM-4.6V Enters with a Bang: High-Performance AI for Images and Videos

Encoderfile: Package Transformer Models into Standalone Executables

TurkColBERT: A Late-Interaction Model for Turkish RAG: Full Local Demo

Hermes 4 is Here: Decentralized and Democratized AI on Solana

HY-Motion 1.0 | Text-to-Motion AI Model - Full Local Hands-on Guide

EmbedAnything - Local Embedding Pipeline for RAG - Full Hands-on Demo

This website uses cookies