…You should be aware of GPU offloading, context window limits, token budgets, and when to move to a new session. Whereas for Claude Code, you only need to know how to open…
…be able to fit the networking cards or the discrete GPU options that it decided would work for Jellyfin and local LLMs. It decided that Ceph was the best storage option, and…
…Tool calling that's baked into the architecture This model is great for practical uses One of the things that's held back local LLMs for agentic workflows is tool calling. Most…
…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 does for free A lot of…
…For Qwen2.5-Coder 32B, you'd need around 20GB of VRAM to run it completely on the GPU. Cards like the RTX 3090, RTX 4090, and, obviously, newer models can handle…
…need Claude, but a local model that's realistic for your hardware, and Qwen 2.5 fits that role well. Qwen Qwen is a comprehensive family of advanced large language models (LLMs…
…As for the tools, I began deploying lightweight utilities that I might need while I’m away from my goblin cave. Pairdrop was the first tool I spun up, and after confirming…
…Of course, these are just my preferred LLM models for my workflow. You shouldn’t hold yourself back from exploring other LLMs based on your hardware setup and workflow.
…Related 3 reasons I really want Intel to release another Battlemage GPU We all need the Intel Battlemage train to keep going Battlemage at high-end was always the GPU gamers needed…
…As for backup: my tried and true, encrypted little physical hard drive. There's no need for massive cloud storage for text and PDF files. Related 4 reasons Open Notebook is the…