project
Desktop local-model runner described as picking up the shipped chat template automatically.
A hardening write-up on LM Studio separates local execution from network isolation, then enforces the second with OS rules rather than trusting the app's own checkboxes.
Reality
The distro's manual says agents are first-class citizens but it will not pick a favourite. Lazy-loaded stubs make that neutrality cheap, until a crash needs a default agent.
Reality
A dev.to writeup drops LangChain, LlamaIndex, hosted vector stores and the cloud model, leaving six files, seven npm packages, and one cloud dependency still in place.
Reality
Qwen 3.8 27B ran on a MacBook Pro from a 17GB GGUF and spent 21 minutes on one SVG. Licensing and access stopped being the blocker; latency and KV cache budgeting became the job.
Reality
Two releases, two licences. Only the 27B is Apache 2.0, and because just 16 of its 64 layers keep a KV cache, long context costs a quarter of the usual memory.
Reality