Want to LEARN how to build useful AI agents that actually get things done? Go here: https://aiagentbuilders.co/yt
Local AI is incredibly powerful — but only if you know how to set it up properly. In this video I share my complete $7,000+ local AI setup: the hardware, the software stack, the models I'm running, and the optimizations that took my inference speed from 16 tokens per second to over 27 — with a single setting change.
Even if you're on consumer hardware, this video will help you understand what you should be running and how to get the most out of whatever you have.
? Tools I Use
Get 10% off with code techwithtim
Openclaw setup: https://www.hostinger.com/techwithtim
VPS setup: https://www.hostinger.com/techwithtim10
Wispr Flow (Best AI Dictation): https://ref.wisprflow.ai/TechWithTim-aug26
? Video Resources ?
Dell GB10 Pro Link: https://www.dell.com/en-us/shop/desktop-computers/dell-pro-max-with-gb10/spd/dell-pro-max-fcm1253-micro/xcto_fcm1253_usx
NVIDIA Models Links: https://www.nvidia.com/en-us/ai-data-science/foundation-models/nemotron/
⏳ Timestamps ⏳
00:00 | Overview
00:24 | Architecture/Setup
01:58 | Hardware
04:11 | What Models I Use
05:27 | MOE Architecture
06:06 | Inference Providers
11:10 | Tailscale/Networking
11:43 | Harnesses & Demos
14:55 | Optimizations
17:11 | Token Speeds
17:49 | Cloud Models
Hashtags
#LocalLLM #HomeAIServer #OpenSourceAI
UAE Media License Number: 3635141