Tracked topic
…But I wanted to test Jan as a local runner so I brought my Gemma 4 E4B GGUF from Hugging Face , it's my go-to for daily chat and creative work…
…Gemma 4 E4B has a context window of 128k tokens. On my hardware, I can comfortably keep the window around 40k, sometimes pushing it up to 70k. This easily gives me 30…
…He also works a lot with Windows systems and networking, especially in mixed environments where things don't always behave the way the documentation says they should. Writing things down is how…
…The model selection is what actually drew me to it over some of the other mobile runners. PocketPal pulls models directly from Hugging Face inside the app, so any GGUF model you…
…like part of VS Code rather than a chatbot running in a separate window. I used Docker Model Runner as the inference backend and Continue as the interface inside VS Code. Docker…
…Related I split my work across five Claude Code subagents and burned through my usage window in under an hour That's the price you need to pay What is Agency, and…
…I've used Claude to orchestrate Codex agents , watched one clean up my messy Windows 11 install without issues, and spent a week working out how far to trust a local LLM…
…The underlying ledger where all of this is tracked is a flat JSON file at %LOCALAPPDATA%\WindowsControlCenter\applied.json, so I can see exactly what state the app thinks Windows is in…
…It's available on Windows, Mac, and Linux. It has a massive provider spread. It hooks into OpenAI, Anthropic, Gemini, DeepSeek, Qwen, plus whichever local models through Ollama or LM Studio. Setting…
…It's the 5-hour rolling window that gets me. Anthropic doesn't publish exact numbers but Opus burns through tokens roughly 3-5x faster than Sonnet, and I run Opus on…