Tracked topic
Gemma is a family of open-weight language models released by Google for text generation and related NLP tasks.
…Most local models lose the plot when you stack negative constraints like that, but Gemma’s instruction following felt sharp. And because it’s the E4B (Edge-4-Billion) variant, I run…
…Once my local model, Gemma 4:e4b , is finished making everything concise and removing any repetitions, I then send it to Claude. As such, Claude spends a lot less time, if any…
…For the last few years, the path to running bigger models locally was simply buying a card with more VRAM. That path has quietly hit a wall in recent years. Consumer VRAM…
…Literally all it took was downloading, unzipping, running one command in the terminal, and that's it. llama.cpp is an open-source C++ runtime for running large language models locally, built…
…centered around my local models Besides my coding tasks, LLMs are just as valuable for my FOSS arsenal. For example, I’ve connected the llama-server running Gemma4-26B-A4B to my…
…None of this would normally be a great week, but I got more done than I expected to, and most of that comes down to having a local LLM setup that runs…
…After migrating through a bunch of setups, I’ve honed in on a local LLM server running on my old Proxmox workstation, and it works surprisingly well for everything from simple prompting…
…Related I replaced ChatGPT and Claude with this powerful local LLM and saved over $20 a month while gaining full control Qwen3.6 runs on my old GPU and does what ChatGPT…
…835, which is pretty solid. Gemma 3 4B got 0.733. Llama 3.2 3B got 0.727. These are all local models you can run on consumer hardware. And then there…
…Right now, AI is designed to run in the cloud. Running it locally is cool, but it's not fully there yet. Once the technology improves, however, I could really see running…