ViewTube

In this video we're going to be look at version 2 of Bonsai from Prism ML. Does this version live up to its big claims? I run through a ...

Don't buy a Mac Mini for local AI without first reviewing the data. This breakdown separates marketing claims from real-world ...

King Crab | My Game https://store.steampowered.com/app/2523690/King_Crab/ https://kingcrabgame.com Want to learn how to ...

Try Granola, the AI notepad I use for every meeting (100% off your first month): https://go.granola.ai/timothy-ruscica By the end of ...

In this review we compare various SSD drives from the internal SSD drives in Macs to USBC, TB4 and TB5 enclosures, showing ...

In this video, I'm testing how the new Mac mini M6 handles serious local AI workloads using Qwen3.8-27B-Splash in LM Studio, ...

What are the best local AI models you should actually be running right now? In this video, I break it down by the hardware you ...

Build Real World AI Automations: https://www.skool.com/real-world-ai-builders Running an AI model locally may feel completely ...

A 34yo Recreational Programmer rants about the future of local LLMs and the shift from local computing to cloud. Let's talk about it ...

It's never been easier to use local AI with Hermes agent Sign up for my free newsletter: https://www.shipitweekly.com/ FULL local ...

Local AI is incredibly powerful, but often you need pretty hefty hardware to run good enough models. The latest Mac Studio M5 ...

In this video I break down how to set up a local AI coding workflow, what hardware you need, how to pick the right model and why ...

A Mac Studio for local AI with 64GB costs about $3500, and even the top M5 Ultra made one long prompt wait 104 seconds before ...

Qwen 3.8 27B quantized to 8.4GB via GSQ-RCO still loses 9 coding points, here's what the benchmarks actually prove vs. Claude.

Your 12GB graphics card has a serious choice to make. Even a compressed 27 billion parameter model is competing for the job!

Qwen Image 2.1 review & tutorial. How to run Qwen Image 2.1 in ComfyUI. Best free open-source AI image generator. Thanks to ...

Bosgame M5 mini PC with 128GB unified memory: can a $2999 local AI desktop actually run 120B models faster than an RTX ...

In the AI world, there are new models almost every week and yet in my Local AI use on Strix Halo (128GB Unified Memory) why ...

We evaluate inference speed (~68–70 tokens/sec) of Ternary Bonsai 2 27B and put its agentic coding capabilities to the test with ...

Every “Which model fits your GPU?” chart on the internet makes the exact same mistake: they only count model weights. But your ...