Turn your USB drive into a fully portable AI setup 🤯

In this video, I’ll show you how to run Local AI Models directly from a USB Drive on Windows, Mac, and Linux using USB-Uncensored-LLM.

This setup allows you to:
✅ Run AI completely offline
✅ Carry your AI setup anywhere
✅ Use Local LLMs with Ollama
✅ Store chats, models, and configs on USB
✅ Run AI on Windows, Mac & Linux
✅ Use a full web-based AI dashboard

We’ll also test:
* Offline AI functionality
* Local AI model setup
* Portable AI chat interface
* Cross-platform AI support
* Phi-3.5 and Gemma models

🔗 GitHub Repo:
https://github.com/techjarves/USB-Uncensored-LLM

⏱️ Timestamps
00:00 Intro
00:12 Offline AI Demo
00:34 USB-Uncensored-LLM Overview
01:06 USB Setup
01:29 MAC Setup & Test
03:44 Windows Setup & Test
05:24 Final Thoughts

If you found this useful, subscribe for more AI setup tutorials, local AI guides, and practical developer tools 🔥

⚠️ Note: Use AI tools responsibly and review permissions before giving access to your system.

#LocalAI #OfflineAI #PortableAI #Ollama #USBDrive #OpenSourceAI #LLM #AItools #DeveloperTools #aisetup

Video assets by Vecteezy
https://www.vecteezy.com

M4 Mac Minis are suddenly selling out — and not because of video editing or creative workflows.

Please keep in mind the date this video was originally released, as availability of the M4 Mac mini has changed due to supply shortages and the impending release of the M5 Mac mini.

People are buying $599 Mac Minis just to run AI.
Over the past few weeks, a viral open-source AI agent has sparked massive interest in running personal AI assistants locally at home. Instead of relying on cloud-based chatbots, creators and tech enthusiasts are setting up always-on AI agents that can manage tasks, automate workflows, and act as persistent personal assistants.

In this video, I break down:
• Why Mac Minis became the go-to AI computer
• What AI agents like Moltbot (formerly Clawdbot) actually do
• Why the $599 Mac Mini price point changed everything
• Whether Mac Minis are really selling out
• The risks of running local AI
• And whether you even need a Mac Mini at all

This isn’t just about Apple hardware — it’s about a shift toward owning your own AI.

If you’re curious about running AI locally, automation workflows, or where personal computing is headed next, this one’s for you.

👇 Let me know in the comments if you’d like a follow-up showing how these AI agents actually work.

M4 Mac mini:
https://amzn.to/3NYBcqq

How to UPGRADE the M4 Mac mini SSD and save hundreds! (Step-by-Step Guide!):
https://www.youtube.com/watch?v=CR9UHe2VG6w

Tech discussed in todays video:
As an Amazon Associate, I earn from qualifying purchases. This means that if you click on one of the product links in this video/description and make a purchase, I may receive a small commission at no extra cost to you. Your support helps me continue creating content like this. Thank you!

🛒 M4 Mac mini 2Tb Internal SSD:
https://amzn.to/4nCp2Tw

NEW!! OWC Express 1M2 80Gb/s Portable NVMe SSD USB4:
https://amzn.to/3JRIJsA

M4 MacBook Air $799:
https://amzn.to/3Jcd2JX

ORICO MiniMate 2TB External SSD:
https://amzn.to/40SL4ta

OWC 5 Port Thunderbolt Hub:
https://amzn.to/49Ca8cH

OWC Express 1M2 Portable NVMe Thunderbolt (USB-C) SSD USB4 Ultra Fast External SSD Drive with Aluminum Heat Sink Enclosure (Enclosure Only):
https://amzn.to/3CpAekA

The NVME SSD I use: Crucial T500 2TB Gen4 NVMe M.2 Internal Gaming SSD:
https://amzn.to/40VPlMK

Xbox Ally:
https://amzn.to/47mXQDA

Bluesound speaker:
https://amzn.to/3EE9i24

The Camera I use:
https://bhpho.to/3V77ELO
https://amzn.to/4bLIecg

The ND Filter I use:
https://amzn.to/3LokyiN

The Key Light I Use:
https://amzn.to/3WRZl7j

The Softbox I use:
https://amzn.to/3T1BVuf

#MacMini #SSDUpgrade #M4MacMini #TechTips #ContentCreation #AppleUpgrade #macOS #FilmmakerGear #DeskSetup #3rdPartySSD

Llama.cpp Web UI + GGUF Setup Walkthrough and Ollama comparisons.
Check out ChatLLM: https://chatllm.abacus.ai/ltf

My USB-C portable hub: https://amzn.to/4kw0hrf
👀 My favorite external drive (dependable): https://amzn.to/3Os9Wi3
👀 Thunderbolt 4 dock: https://amzn.to/3yVRicC

⚡ *Other gear I use:* https://www.amazon.com/shop/alexziskind

▶️ M2 MacBook Air | INSTANTLY connect 4K monitors - https://youtu.be/KLI65HnvNMg
▶️ Unity on Steroids M3 Max and RTX 4090m - https://youtu.be/COpEtHzdPG0
▶️ INSANE Machine Learning on Neural Engine - https://youtu.be/Y2FOUg_jo7k
▶️ Ultimate Web Developer MacBook - https://youtu.be/72fneIUHXyY
▶️ This is what spending more on a MacBook Pro gets you - https://youtu.be/iLHrYuQjKPU

▶️ Apple Silicon and Developers Playlist - https://youtube.com/playlist?l....ist=PLPwbI_iIX3aR88m

Developer productivity Playlist - https://www.youtube.com/playli....st?list=PLPwbI_iIX3a

— — — — — — — — —

❤️ SUBSCRIBE TO MY YOUTUBE CHANNEL 📺

Click here to subscribe: https://www.youtube.com/@AZisk?sub_confirmation=1

— — — — — — — — —

📱LET'S CONNECT ON SOCIAL MEDIA

ALEX ON TWITTER: https://twitter.com/digitalix

— — — — — — — — —

Join this channel to get access to perks:
https://www.youtube.com/channe....l/UCajiMK_CY9icRhLep


⏱️ Chapters
00:00 – Local LLMs, many stacks
01:05 – Building from source
04:15 – Picking a GGUF model
07:56 – New Llama.cpp Web UI
09:06 – Ollama UI & speed check
10:44 – Ollama’s concurrency limit
11:48 – Llama.cpp parallel chats

#llm #llamacpp #macbook

Access your devices securely from anywhere with TwinGate: https://ntck.co/dgxspark


NVIDIA just sent me their smallest AI supercomputer that fits in the palm of my hand. This is the NVIDIA DGX Spark, an AI powerhouse with a Grace Blackwell Superchip that can run up to 200 billion parameter models. In this video, I pin it against my insane dual RTX 4090 AI Server “Terry” to see if this new category of computing can really compete.


**Correction:** The DGX Spark uses the GB10 Grace Blackwell Superchip (not GP10).


RESOURCES / LINKS:

⚡ Nvidia DGX Spark (launches Oct 15) : https://nvda.ws/4nFFtPT

🍏 AI Supercomputer Video (5 Mac Studios): https://youtu.be/Ju0ndy2kwlw?si=hiWzpU3jIOhHf7iv

🗣️ Cloning my voice into an AI Assitant: https://youtu.be/3fg7Ht0DSnE?si=ePo1JjrC6gnChWPb





🔥🔥Join the NetworkChuck Academy!: https://ntck.co/NCAcademy



**Sponsored by Twingate







SUPPORT NETWORKCHUCK
---------------------------------------------------
➡️NetworkChuck membership: https://ntck.co/Premium
☕☕ COFFEE and MERCH: https://ntck.co/coffee

🆘🆘NEED HELP?? Join the Discord Server: https://discord.gg/networkchuck

STUDY WITH ME on Twitch: https://bit.ly/nc_twitch

READY TO LEARN??
---------------------------------------------------
-Learn Python: https://bit.ly/3rzZjzz
-Get your CCNA: https://bit.ly/nc-ccna

FOLLOW ME EVERYWHERE
---------------------------------------------------
Instagram: https://www.instagram.com/networkchuck/
Twitter: https://twitter.com/networkchuck
Facebook: https://www.facebook.com/NetworkChuck/
Join the Discord server: http://bit.ly/nc-discord




AFFILIATES & REFERRALS
---------------------------------------------------
(GEAR I USE...STUFF I RECOMMEND)
My network gear: https://geni.us/L6wyIUj
Amazon Affiliate Store: https://www.amazon.com/shop/networkchuck
Buy a Raspberry Pi: https://geni.us/aBeqAL
Do you want to know how I draw on the screen?? Go to https://ntck.co/EpicPen and use code NetworkChuck to get 20% off!!
fast and reliable unifi in the cloud: https://hostifi.com/?via=chuck

“NVIDIA DGX Spark Review: The AI Supercomputer That Fits in Your Hand”


“Can NVIDIA’s DGX Spark Beat My Dual 4090 AI Server?”


“NVIDIA DGX Spark vs. RTX 4090: AI Battle Test”


“Is the $4,000 NVIDIA DGX Spark Worth It?”


“Running 200B Parameter Models on a Handheld AI Server”


“Grace Blackwell Superchip Explained: NVIDIA’s Tiny Powerhouse”


“Local AI Just Changed Forever: DGX Spark Review”


“How I Built a Mini AI Server That Trains Models Locally”


“Speculative Decoding on the DGX Spark: What It Actually Does”


“DGX Spark vs. Terry: Local AI Showdown”


“Running Llama 3 and DeepSeek on NVIDIA’s DGX Spark”


“The Most Powerful Mini AI Computer Yet?”


“Fine-Tuning Models Locally with NVIDIA DGX Spark”


“Can You Train AI Models at Home with This Device?”


“NVIDIA’s Tiny AI Server for Developers (Full Breakdown)”


“The Future of Local AI: Hands-On with DGX Spark”


“Running FP4 Models on NVIDIA’s New DGX Spark”


“NVIDIA DGX Spark Review: A Developer’s Dream Machine?”


“How Fast Is the DGX Spark? Real Benchmark Results”


“The Palm-Sized AI Supercomputer from NVIDIA”



#NVIDIA #DGXSpark #AIserver

Get your own VPS and set up OpenClaw: https://hostinger.com/ncopenclaw Use code NETWORKCHUCK!

OpenClaw has 308K GitHub stars — more than React, more than the Linux kernel. But what IS it actually? I set it up on a VPS, gave it a Telegram bot, and watched it build a news briefing and server monitoring dashboard in minutes — something that took an entire n8n workflow video to do before. But I also kinda hate it. In this video, I cut through the hype and give you my honest take as someone who built the same thing with Claude Code before OpenClaw existed.

In this video, you'll learn how to install OpenClaw on a Linux VPS in under 5 minutes, connect it to Telegram, build an AI news briefing agent and IT monitoring dashboard, understand the four pillars of OpenClaw (AI models, channels, memory, and tools), configure security with the built-in security audit, set up tool profiles and red lines, and decide if OpenClaw is right for you. Whether you're an AI enthusiast drowning in hype or a sysadmin curious about AI agents, this covers everything from one-line install to hardened security config.


RESOURCES / LINKS:
🎓 NetworkChuck Academy (OpenClaw Course):https://ntck-ac.co/oc1
💻 GitHub Setup Guide (all commands): https://github.com/theNetworkChuck/openclaw-setup
🌐 OpenClaw: https://openclaw.ai
🛠️ ClawHub (Skills Directory): https://clawhub.com
🛠️ Hostinger VPS: https://hostinger.com/ncopenclaw
📺 n8n Automation Video: https://youtube.com/watch?v=ONgECvZNI3o
☕ NetworkChuck Coffee: https://networkchuck.coffee


TIMESTAMPS:
0:00 - OpenClaw stressed me out (308K GitHub stars)
1:44 - Setting up OpenClaw in 5 minutes on a VPS
4:22 - Connecting Telegram and hatching your agent
7:30 - Project 1: AI news briefing (one sentence vs entire n8n workflow)
8:14 - Project 2: AI IT engineer monitoring your own server
9:34 - What IS OpenClaw actually? (gateway + 4 pillars)
15:07 - Tools, cron jobs, and heartbeats
17:08 - ClawHub skills, browser, and sub-agents
19:27 - Why everyone freaked out (my honest take)
20:55 - Securing your OpenClaw instance
30:01 - My verdict: how I actually use OpenClaw


**Sponsored by Hostinger



SUPPORT NETWORKCHUCK:
☕☕ COFFEE and MERCH: https://ntck.co/coffee


READY TO LEARN??
🔥🔥Join the NetworkChuck Academy!: https://ntck.co/NCAcademy
📚 CCNA Course: https://ntck.co/ccna


FOLLOW ME EVERYWHERE:
Instagram: https://www.instagram.com/networkchuck/
X/Twitter: https://x.com/networkchuck
Facebook: https://www.facebook.com/NetworkChuck/
Join the Discord server: https://ntck.co/discord


Some links in this description are affiliate links. If you buy through them, I may earn a small commission at no extra cost to you.


#openclaw #aiagents #networkchuck

I built a fully functional, talking BMO from Adventure Time using a Raspberry Pi 5 and local AI models.

In this video, I break down the hardware I used, designing and assembling a 3D printed enclosure, and using Ollama to build a battery-powered, local, voice activated AI agent.

0:00 Intro
2:25 Hardware breakdown
4:10 Creating the enclosure
7:15 Software deep-dive
15:49 Assembling BMO
18:55 Full AI Agent demo
21:54 Closing thoughts

🔧 Hardware:
- Raspberry Pi 5 (16GB)
- Raspberry Pi Camera Module v2
- Pimoroni NVMe Base Duo
- Geekworm X1203 5V UPS shield
- Freenove 5 Inch Touchscreen Monitor
- Adafruit Feather 32u4 Basic Proto
- Mini USB Microphone
- Mini External USB 2.0 Speaker
- 6mm momentary switches x 7
- 5x2mm round magnets x 16
- 3.7V lithium ion battery

🔧 The Tech Stack:
- LLM & VLM (Brain): Gemma 3 + Moondream 2 (via Ollama)
- STT (Ears): Open Wake Word + Whisper
- TTS (Voice): Piper TTS

🔧 STL & PCB files: https://www.printables.com/mod....el/1582055-bmo-from-

🔧 GitHub repository: https://github.com/brenpoly/be-more-agent

🛡️ A Note on Safety (Please Read):
I have done my best to ensure this code is safe and clean. However, you should never blindly trust public code. As much as you may like this project, I'm still a stranger from the internet with one viral video 😅. Stay curious, but stay safe!

🔒 Good Security Practice:
- Always scan files before running them.
- Read through the Python scripts (.py files) to understand what they are doing before you execute them.
- If you are new to this, ask a friend (or an AI!) to help you review the code first.

Get the 10-Step Security PDF Checklist here: https://danieljindoo.substack.com/
Join Our Semi-Private Community: https://discord.gg/HmbPtVy6Eq
Join Operators: https://www.youtube.com/channe....l/UCz21u_dPpYlJ-XyLc

Your local AI agents setup is leaking data right now, and you probably don't even know it. Running an LLM locally doesn't automatically make it private & safe. If your machine connects to the internet, you’ve basically bought your own house and left every single window open.

In this video, I break down the 7 vulnerabilities hiding in plain sight in your local AI stack-from browser extensions reading your chats to OS telemetry and exposed servers. Whether you're using Ollama, LM Studio, or vLLM, if you handle client data or sensitive business info, you need to lock this down.

No enterprise BS. Just real implementation and the exact 10-step security checklist I use.

⏳ TIMESTAMPS:

00:00 - The "Local = Safe" Myth Debunked
00:14 - Renting vs. Owning: Levels of AI Ownership
01:09 - Why You Are Probably at Level 1 (Exposed)
01:45 - Leak 1: Exposed AI Servers & APIs
03:00 - Leak 2: Browser Extensions Reading Everything
04:10 - Leak 3: Cloud Sync Auto-Uploading Chats
05:16 - Leak 4: Malicious AI Models & Poisoned Weights
06:30 - Leak 5: OS Telemetry (Windows Recall & Mac)
07:36 - Leak 6: Legal Obligations (GDPR, HIPAA, CCPA)
09:01 - The 10-Step Local AI Security Checklist
10:07 - Download the Free Setup Guide

Got questions about securing your specific SMB stack? Drop a comment below and let's troubleshoot.

Subscribe for outcome-based AI use cases. Information is free. Trust is rare. I only show you what I've actually built.

FIND ME ON SOCIALX/Twitter:
https://x.com/Jdaniel1216/Instagram:
https://www.instagram.com/jinni_doo/LinkedIn:
https://www.linkedin.com/in/hy....oungjin-doo-a1939423
Newsletter: https://danieljindoo.substack.com/
Website: / https://doomade.com/

Advanced RAG 101 - build agentic RAG with llama3

Get free HubSpot report of how AI is redefining startup GTM strategy: https://clickhubspot.com/4hx

🔗 Links
- Join my community: https://2ly.link/1zq90
- Follow me on twitter: https://twitter.com/jasonzhou1993
- Join my AI email list: https://www.ai-jason.com/
- My discord: https://discord.gg/eZXprSaCDE
- Corrective RAG agent: https://github.com/langchain-a....i/langgraph/blob/mai
- LlamaParse: https://github.com/run-llama/llama_parse
- Firecrawl: https://www.firecrawl.dev/
- Jerry Liu build production-ready RAG: https://www.youtube.com/watch?v=TRjq7t2Ms5I


⏱️ Timestamps
0:00 Intro
1:33 How to give LLM knowledge
3:05 Problem with simple RAG
5:55 Better Parser
9:01 Chunk size
11:40 Rerank
12:39 Hybrid search
13:10 Agentic RAG - Query translation
14:35 Agentic RAG - metadata filtering
15:52 Agentic RAG - Corrective RAG agent
17:33 Install LLama3
18:00 Code walkthrough


👋🏻 About Me
My name is Jason Zhou, a product designer who shares interesting AI experiments & products. Email me if you need help building AI apps! ask@ai-jason.com

#llama3 #rag #llamaparse #llamaindex #gpt5 #autogen #gpt4 #autogpt #ai #artificialintelligence #tutorial #stepbystep #openai #llm #chatgpt #largelanguagemodels #largelanguagemodel #bestaiagent #chatgpt #agentgpt #agent #babyagi

Access your devices securely from anywhere with TwinGate: https://ntck.co/ai_terminal


Still using AI in the browser? You’re doing it the slow way. In this video, I BREAK OUT of the GUI and show you how AI in the terminal (Gemini CLI, Claude Code, Codex and OpenCode) makes me 10x faster. We’ll install the tools (Mac/Windows/Linux), spin up project aware context files, and unlock terminal AI superpowers. I’ll also show my daily workflow for keeping multiple AIs in sync across the same folder.


RESOURCES / LINKS:

Commands / Walkthrough: https://github.com/theNetworkC....huck/ai-in-the-termi
Gemini CLI: https://ai.google.dev/gemini-api
Claude Code: https://www.claude.com/product/claude-code
OpenCode: https://opencode.ai/


TIMESTAMPS:

0:00 - Intro
1:09 - Segment 1: The Terminal Superpower (Gemini)
8:43 - Segment 2: Claude Code
17:59 - Segment 3: ALL THE TERMINALS!!!
20:31 - Segment 4: Meta-Proof
26:29 - Segment 5: Open Code


🔥🔥Join the NetworkChuck Academy!: https://ntck.co/NCAcademy



**Sponsored by Twingate







SUPPORT NETWORKCHUCK
---------------------------------------------------
☕☕ COFFEE and MERCH: https://ntck.co/coffee

🆘🆘NEED HELP?? Join the Discord Server: https://discord.gg/networkchuck

STUDY WITH ME on Twitch: https://bit.ly/nc_twitch

READY TO LEARN??
---------------------------------------------------
-Learn Python: https://bit.ly/3rzZjzz
-Get your CCNA: https://bit.ly/nc-ccna

FOLLOW ME EVERYWHERE
---------------------------------------------------
Instagram: https://www.instagram.com/networkchuck/
Twitter: https://twitter.com/networkchuck
Facebook: https://www.facebook.com/NetworkChuck/
Join the Discord server: http://bit.ly/nc-discord




AFFILIATES & REFERRALS
---------------------------------------------------
(GEAR I USE...STUFF I RECOMMEND)
Use n8n to automate EVERYTHING: https://ntck.co/n8n
Want to browse securely? Try my ZERO-TRUST browser: https://browser.networkchuck.com/
Do you want to know how I draw on the screen?? Go to https://ntck.co/EpicPen and use code NetworkChuck to get 20% off!!



“Stop Using AI in the Browser: Terminal Is 10x Faster”
“Gemini CLI + Claude Code: My AI Terminal Workflow”
“AI in the Terminal Changed Everything (Goodbye GUI)”
“Claude Agents in Your Terminal: Multi-Task Like a Boss”
“The Ultimate AI Dev Environment: Gemini, Claude, OpenCode”
“How I Sync Multiple AIs on One Project (No Copy/Paste)”
“Own Your Context: AI Projects That Live on Your Drive”
“Terminal AI for Writers, Hackers, and Builders”
“Claude Code Agents Explained: Fresh Context Windows!”
“Open-Source Terminal AI That Runs Local Models”
“Build an AI Terminal Stack: Install, Configure, Dominate”
“From Browser Chaos to Terminal Flow (Full Setup)”
“Headless AI: Run Prompts from Bash & Scripts”
“Output Styles & Agents: Claude Code’s Secret Weapons”
“Why I Use 3 Terminal AIs at Once (and How)”
“Replace Your Notes App with AI-Backed Context Files”
“Production AI Workflows with Git + Terminal Tools”
“Zero Trust for AI: Secure Your Files Before You Start”
“Turn Your Terminal Into a Superpower with AI”



#terminal #AI #claudecode

US President Donald Trump says an agreement with Iran has been "largely negotiated" and details will be announced soon.

The deal would include the reopening of the Strait of Hormuz, he said on Saturday, without giving further details.

Iranian foreign ministry spokesman Esmaeil Baqaei earlier told state television that US and Iranian positions had been converging in the last week, but warned that did not mean agreements would be reached on key issues and accused the Americans of "contradictory statements".

Subscribe to our channel here: https://bbc.in/bbcnews

For the latest news download the BBC News app or visit BBC.com/news

#BBCNews

Military analyst Robert Clark looks at the latest in the Iran war as Donald Trump's comments show potential cracks in his relationship with Israeli prime minister Benjamin Netanyahu.

#middleeast #iran #war #usa #skynews

SUBSCRIBE to our YouTube channel for more videos: http://www.youtube.com/skynews
Follow us on Twitter: https://twitter.com/skynews
Like us on Facebook: https://www.facebook.com/skynews
Follow us on Instagram: https://www.instagram.com/skynews
Follow us on TikTok: https://www.tiktok.com/@skynews

For more content go to http://news.sky.com and download our apps: Apple https://itunes.apple.com/gb/ap....p/sky-news/id3163919 Android https://play.google.com/store/apps/details?id=com.bskyb.skynews.android&hl=en_GB

Listen to our new podcast This is Why, available for free here: https://podfollow.com/thisiswhy

To enquire about licensing Sky News content, you can find more information here: https://news.sky.com/info/library-sales

The UK has agreed to allow the US to use British bases to launch strikes on Iranian sites targeting the Strait of Hormuz.

US President Donald Trump said the UK "should have acted a lot faster", while Iran's Foreign Minister Abbas Araghchi claimed Sir Keir was "putting British lives in danger”.

Trump also said the US is considering “winding down” operations against Iran, but that other nations must guard the Strait of Hormuz - a vital shipping lane for oil.

But Iran’s foreign minister has said "it does not appear that the United States is prepared to halt its aggression".

Subscribe here: http://bit.ly/1rbfUog

For more news, analysis and features visit: www.bbc.com/news

#US #Israel #Iran #BBCNews