Improving LLM prefill on the NVIDIA GeForce RTX 4060 mobile

The Acer Nitro V15 has a discrete nvidia GeForxe RTX 4060 mobile. Turns out, the default firmware leaves some performance untapped [GPU].1. follow the project instructions [GPU] to download, build and install.2. specifically, the 4060m requires a kernel parameter in grub: "gpu_unlock.targets=0000:01:00.0 gpu_unlock.ad107_experimental=1"You'll have to find the exact address with lspci. Yes, it needs the … Continue reading Improving LLM prefill on the NVIDIA GeForce RTX 4060 mobile →

Running even larger LLMs on small hardware

In a previous post [GM4] we ran gemma4 12B on a 16GB RAM budget; today we'll push the envelop and run deepseek-r1:14b-qwen-distill-q4_K_M on the same budget. While last time we got away by fiddling with the model definition, today we'll have to reconfigure the OS itself (in addition to fiddling with the model definition). While … Continue reading Running even larger LLMs on small hardware →

Adding an entry to Nautilus’ context menu

I'm missing, dearly, the "Play with VLC" context menu entry in Ubuntu 24.04. There's a cumbersome workaround(open -> with -> *scroll scroll scroll* -> VLC), but I want something faster. What started as a side quest for some convenience eventually taught me how to add arbitrary functionality to Ubuntu's file manager context menus. Step 1: … Continue reading Adding an entry to Nautilus’ context menu →

Minimising screen brightness in Ubuntu

I like working at night, but nearly every laptop I've tried with Ubuntu can't reduce screen brightness to comfortable levels. Thankfully there is a convenient workaround. Under Ubuntu 24.04 / Wayland find Accessibility -> Zoom -> Colour filters and adjust to your liking. You probably want to pin the magnification factor to 1.00, too. The … Continue reading Minimising screen brightness in Ubuntu →