Tracked topic
…Subscribe by modifying your newsletter preferences ! Finding a mobile LM Studio I actually found something better LM Studio doesn't have a mobile version, so of course I went looking for an…
…LM Studio See at LM Studio
…There are something like 356 versions of it on LM Studio, all looking pretty much the same, so picking one was a headache before anything else. I went with the QAT Q4…
…Looking back, the number of times I opened LM Studio or llama.cpp dropped massively, which must count for something. Related I ran Gemma 4 and Qwen 3.5 for the same…
…With Open Notebook, though, the data sits on your machine, and you get to pick which of the 18+ supported AI providers (OpenAI, Anthropic, Google, Ollama, LM Studio, and more) actually gets…
…Meanwhile, the 32GB Nvidia RTX card in my PC has largely been sitting idle, other than loading the occasional local model via LM Studio. Every time I hit my token limits, I…
…Push it too high and you spill over into shared system RAM, and that's where things get bad - LM Studio's own performance penalty for spilling is up to 30x slower…
…You just pick OpenAI from the provider dropdown and point it at the LM Studio localhost endpoint (http://localhost:1234/v1) since LM Studio exposes an OpenAI-compatible API anyway. Type any…
…LM Studio See at LM Studio
…Let’s say I wanted my LM Studio models to access my home lab notes. All I’d have to do is add this MCP server inside LM Studio, enable it in…