Yes you read that correctly folks, Qwen has smashed this one out of the park. Thanks to the power of Quantization (the art of compressing models like ZIP files), we're able to get the model size down from 93gb to just 22GB while retaining 90% of it's intelligence.. Note it's an 80b model so in this case you'll still have a fantastic time even with a Q1 or Q2 version. I'm using Q2 K_M and it hasn't failed once. You too can run this incredible model completely locally, offline and without paying a single dollar. We'll cover this in depth in tomorrow's live so don't forget to tune in!

Emergency video that just had to be made.

Quick one: If you're not using terminal based agents yet.. You're already behind Here's Why. Terminal Agents are: - Lightweight - only use minimal compute resources to run - Can run for hours if not days - without any human intervention required ( if you know what you're doing) - Can work on multiple projects at once - Come back once the build's complete And so much more. Big question though.. Do I have to pay? No. That's why you're here :) You can use Ollama with Claude Code and get shit done! Here's how it works. Claude Code is Anthropic’s agentic coding tool that can read, modify, and execute code in your working directory. Open models can be used with Claude Code through Ollama’s Anthropic-compatible API, enabling you to use models such as qwen3-coder, gpt-oss:20b, or other models. Install Install Claude Code: macOS / Linux curl -fsSL https://claude.ai/install.sh | bash Windows irm https://claude.ai/install.ps1 | iex Usage with Ollama Claude Code connects to Ollama using the Anthropic-compatible API. Set the environment variables: export ANTHROPIC_AUTH_TOKEN=ollama export ANTHROPIC_BASE_URL=http://localhost:11434 Run Claude Code with an Ollama model: claude --model gpt-oss:20b Or run with environment variables inline: ANTHROPIC_AUTH_TOKEN=ollama ANTHROPIC_BASE_URL=http://localhost:11434 claude --model gpt-oss:20b CLOUD MODELS ALSO WORK AND WORK VERY WELL! Note: Claude Code requires a large context window. We recommend at least 32K tokens. Free. Unlimited coding. All at your disposal. Happy building! PS. Do you want a live stream for this?

So this has been a bit of a learning experience for me. I’ve tried to find tuning models in the past, but to know what was available and not get anywhere, things didn’t quite click. However, this time, I took a different approach—using the latest Liquid AI model, LFM 2.5.1b.1.2. This was a game-changer for me because I wanted to train a reasoning model that could think quickly, produce fast outputs, and excel at coding tasks. And it worked! We’ve successfully implemented it, and it’s now available for you to try out on your devices. We’re excited to see how you’ll use it and can’t wait to hear your thoughts. This model is designed to run efficiently across a variety of devices—think smartphones, Raspberry Pi, computers, or even a laptop. The possibilities are truly endless! I’m really looking forward to seeing what we can achieve with this technology. And here’s a quick question: Would you ever want to build your own model and explore its potential for specific use cases?

If we were to provide our Skool members with free, unlimited access to ONE of the following things as a thank you for being here. Which one would you pick?