carteakey.dev

Note: This post was drafted with significant AI assistance, synthesizing notes, bench results, and scripts from the l3ms homelab toolkit and the series of model-running posts on this site.

Google's release of the QAT (Quantization-Aware Training) variants of Gemma 4 has changed the game for local inference on consumer hardware.

I had $300 API credits to burn and nothing else to show for it.

I spent the last couple of days doing the extremely normal thing where you turn a trailer into 1,290 individual frames, send the frames through image models, stitch them back together at 12fps, and then slowly realize the actual boss fight is black bars.

Update (May 20, 2026): Gemma 4 MTP support has arrived in mainline llama.cpp via PR #23398!

Update (June 16, 2026): Ran a comprehensive benchmark sweep on the latest mainline build of llama.cpp using a custom local benchmark harness comparing Q4_K_XL vs.

I like Obsidian a lot.

Qwen3.6 continues the strong trend of highly capable open models, and the 35B-A3B MoE variant hits a sweet spot for consumer hardware.

I thought this would take one evening.

The hype around openclaw - and every other claw derivative - seems to be fading a bit as reality checks in.

Google DeepMind's Gemma 4 family is out-truly open with Apache 2 licenses, multimodal with support for text, image, and audio, and efficient enough to run on-device.

When I moved away from Jekyll a couple years ago, I didn't expect to end up with something I'd name.

I've been a fan of WindowSwap for a while - the idea is simple and kind of beautiful.

I've been thinking about what kind of pages belong on a personal website that aren't blog posts and aren't portfolio entries.

A few weeks ago I came across this post on Marginalia showing that new Hacker News accounts are ten times more likely to use em dashes than older ones.

I started at 3 PM and called it morning.

You probably don't need >$100 plans for coding or toying with OpenClaw.

TL;DR # Hardware: i5-12600K (6P + 4E), RTX 4070 (12 GB), 64 GB DDR5 6000 MT/s, Linux (CachyOS, CUDA 13.0).

Note: Writing unfiltered, raw and undeveloped thoughts.

TL;DR: Perform exploratory data analysis on Databricks by "volleying" with AI agents like Claude or Copilot - iterate quickly with SQL queries, and generate notebooks automatically.

I had this old webcam lying around which I haphazardly bought during the "COVID webcam shortage" era.

Gemini's Nano-banana is literally nuts.

Just out of curiosity, I wanted to see how well GPT‑OSS (the 120B variant) performs on the same coding‑related prompts that GPT‑5 highlights in its Demo.

Authorship note Parts of this post were drafted/refined with the help of gpt-oss-120b itself.

Obsidian is one of the most useful pieces of software I've used.

Note: This post was partially augmented by AI-specifically, Claude Sonnet 4.

With all respect to the incredible talent and creativity at Studio Ghibli and Miyazaki, I genuinely can’t stop myself from using ‘convert to ghibli’ - or as everyone now calls it, ‘ghiblify’ - on every image I see after the recent 4o image generation upda…

I am a huge fan of self-hosting, and one of the things i use is Immich to store precious photos of me and my family.

My blog uses ~~AI~~, no seriously!

Warning: Borderline shitpost.

Meta recently released their CodeLlama models, which are fine tuned for code completion and analysis.

The thought of myself mindlessly scrolling through a world of increasingly diluted content, especially with the advent of generative AI, repulses me to no end.

So you have a Windows PC with WSL2 installed in it and want to SSH into it from another device like a Mac.

I recently switched to a Macbook Air (M2) as my primary computer, leaving behind a loud and heavy ASUS-FX505 which I had bought as a gaming PC and served me well for over 3 years.

This is in continuation of my older post.

Fedora and openSUSE are removing H.264, H.265, and VC-1 VA-API video codecs support from Mesa to avoid potential patent issues.

So, after a lot of procrastination, I decided to migrate my old site - which was based on Jekyll's popular theme - Minimal Mistakes and hosted on GitHub Pages.

Heroku is ending its free tier starting 28th November 2022.

Obsidian is a great note-taking application.

The power of search engines is astonishing.