Tracked topic
Gemma is a family of open-weight language models released by Google for text generation and related NLP tasks.
…Say you're setting up a local LLM for coding, and you settle on three options: Devstral 2 123B, Qwen3 Coder Next 80B, and Gemma 4 31B. Devstral 2 is the most…
…I don't really need a local LLM. I started using them out of novelty more than anything, and the local-only workflow was a nice addition. But when the power's…
…So you're not waiting on your runner to catch up to use the newest open weights. Related Ollama is still the easiest way to start local LLMs, but it's the…
…Local LLMs aren't really necessary, but they were in this case Most of us can skip local LLMs and be completely fine without them. They're not actually necessary, but we…
…Local LLMs aren’t just chatbot replacements Having spent hours configuring the right LLM pipelines for my FOSS models, I have to admit that local AI tools are far more useful than…
…Look at Open Design for example - Claude Design dropped, I blinked, and Open Design suddenly appeared as a direct alternative you can use locally. I've been experimenting with local AI most…
…So what does this tell us? Well, your local AI agent doesn't need to be big. It just needs to be good at calling tools. Model size doesn't predict tool…
…I can put my old graphics cards to good use Like most LLM-hosting enthusiasts, I started my journey by hosting local models on Ollama , and it served me well for the…
…Turns out, the cluster’s performance was worse than a standalone SBC I blame slow network provisions for this bottleneck Since I was using the fairly lightweight Gemma 3 4B, I expected…
…Llama, Gemma, and Deepseek. I opted to install the smallest version of each model, as I only had 32GB of space on the SD Card. Using LLMs on the SBC was responsive…