Brendan McKeag

Stable Diffusion 3.5 delivers a major quality leap, fixing past flaws while generating photorealistic images from minimal prompts. Learn what's new, how.

NVidia's Llama 3.1 Nemotron 70B is outperforming larger and closed models on key reasoning tasks. In this post, Brendan tests it against a long-unsolved.

Nemotron 70B is NVIDIA's latest open model and it's climbing the leaderboards. But how does it perform in the real world, and can it solve your toughest.

Skip the front ends, learn how to use Jupyter Notebook on Runpod to run Stable Diffusion directly in Python. Great for devs who want full control.

Large language models can write poetry and solve logic puzzles, but fail at tasks like counting letters or doing math. Here's why, and what it tells us.

Lower VRAM usage and improve inference speed using GGUF quantized models in KoboldCPP with just a few environment variables.

GGUF quantizations make large language models faster and more efficient. This guide walks you through using KoboldCPP to load, run, and manage quantized.