ViewTube

A 744-billion-parameter AI model running locally on a machine with just 25GB of RAM sounds impossible. But Colibrì is changing ...

Everyone's talking about Fable 5 and GPT-5.6. But can a small model running on your own computer actually build something ...

Ready to become a certified watsonx AI Assistant Engineer? Register now and use code IBMTechYT20 for 20% off of your exam ...

LLM providers are not safe for you ‼️ There are 4 reasons to switch 100% local I'm sharing my experience using local GenAI ...

Subscribe to our weekly newsletter to get a Free System Design PDF (368 pages): https://newsletter.bytebytego.com.

GLM-5.2 has 744 billion parameters, and colibrì, a 1300-line C engine, runs it on a laptop with 25GB of RAM and no GPU.

In this video I want to check out BottleCap AI's finetune on Qwen 27B MTP which claims to have 50% less thinking tokens on ...

Learn what it takes to build a custom PC dedicated to running AI agenda and Local LLMs entirely offline, free of any cloud ...

Local LLMs are finally good enough at coding and this video is to show you just how good. I have a frontier model and a local ...

Access all my courses here and get up to 10% off forever with the coupon code "off10" https://academia.holamundo.io/bundles ...

Get 25% off SEO Writing using my code TWT25 → https://seowriting.ai/?utm_source=youtube&utm_medium=tech_with_tim In this ...

Click this link https://boot.dev/?promo=TECHWITHTIM and use my code TECHWITHTIM to get 25% off your first payment for ...

Dave tests llama3.1 and llama3.2 using Ollama on a Raspberry Pi, a Herk Orion Mini PC, a 3970X, an M2 Mac Pro, and a ...

In this video CJ guides you through the wide world of local AI. He shows how he set up his new 128GB memory mini PC and gives ...

Ollama runs open LLMs locally. One command pulls a model like GLM, DeepSeek, Qwen or Gemma and serves it on your own ...

GLM 5.2 might be the best open-weight model ever released, but "running it yourself" means 400GB of VRAM, a $75000 GPU box ...

... 70B LLM - https://youtu.be/xyKEQjUzfAk RAM torture test on Mac - https://youtu.be/l3zIwPgan7M ⚡ FREE Local LLMs ...

A local LLM on a six-year-old graphics card can write your code all day, for free. So why isn't every developer running one?

DeepSeek ran a 284-billion-parameter model on a laptop. A year ago that took a rack of GPUs. Local LLM inference got that good, ...