4 levels of LLMs (on the go)
I put four portable systems to the local LLM test. 🛒 Gear Links 🛒 💻🔄 K8 Plus with 32GB RAM: https://amzn.to/3FnjJY0 📦🎮 GPU2: https://onexplayerstore.com/products/... 🛠️🚀 96GB RAM kit: https://amzn.to/3ZhQ4qR 🍏💥 M4 Max: https://amzn.to/3XIRw3X 🎧⚡ RTX 4090: https://amzn.to/3YvvHpg 🛠️🚀 Mini PC with Oculink: https://amzn.to/3UgLNAK 📦🎮 My gear: https://www.amazon.com/shop/alexziskind 🎥 Related Videos 🎥 🤯 Cheap mini runs a 70B LLM -    • Cheap mini runs a 70B LLM 🤯  🤖 It’s over…my new LLM Rig -    • It’s over…my new LLM Rig  🌗 RAM torture test on Mac -    • TRUTH about RAM vs SSD UPGRADES for MacBook  🛠️ FREE Local LLMs on Apple Silicon | FAST! -    • FREE Local LLMs on Apple Silicon | FAST!  🛠️ Set up Conda -    • python environment setup on Apple Silicon ...  🤖 INSANE Machine Learning on Neural Engine -    • INSANE Machine Learning on Neural Engine |...  🛠️ Developer productivity Playlist -    • Developer Productivity  🔗 AI for Coding Playlist: 📚 -    • AI  — — — — — — — — — ❤️ SUBSCRIBE TO MY YOUTUBE CHANNEL 📺 Click here to subscribe:    / @azisk  — — — — — — — — — Join this channel to get access to perks:    / @azisk  — — — — — — — — — 📱 ALEX ON X:   / digitalix  #machinelearning #llm #softwaredevelopment
Smaller and cheaper dev machine that runs LLMs
I built a private AI mini-cluster with Framework Desktop
Local AI Explained | Hardware, Setup and Models
Your local LLM is 10x slower than it should be
RTX Spark Is Already Making People Mad
I Investigated India’s Biggest Smartphone Controversy
The Flipper One is Finally Here (And It's Huge)
I Hacked This Temu Router. What I Found Should Be Illegal.
NVIDIA Monopoly is DEAD | OPEN-SOURCE Chips Are HERE!
This Shouldn’t Be Able to Run 120B Locally
I Tested the Cheapest Path to 96GB of VRAM
Stop Letting Local LLMs Destroy Your Storage… I Built a Fix
I Challenged an Employee to Build a budget AI PC… Big Mistake
Want to Run AI Agents Locally? Here is The Bare Minimum Setup/Build
Private & Uncensored Local LLMs in 5 minutes (DeepSeek and Dolphin)
Expensive RTX 5090 for LLMs? NO. Use This Instead. (SXM2 + Z8 G4, #RACERRRZ)
Testing Qwen 3.6 Locally on Easy, Medium, and Hard Coding Tasks
Cheap mini runs a 70B LLM 🤯
Why We All Gave Up on Smart Homes
