Run models on hardware you control. No API key, no per-token bill, no cloud dependency. Structured reviews and enforced documentation are how you tell which ones are actually worth running.
8 models · Text generation · All licences · Apple M-series 16 GB
Good for drafting HTML, CSS, and JavaScript snippets and explaining how they work. Not reliable for security sensitive code such as authentication or payment handling without human review.
Good for writing and refactoring code across common languages and explaining unfamiliar codebases. Still makes mistakes on edge cases, so treat its output as a draft that needs review, not a ready merge.
Good for a lightweight customer chat assistant that answers common questions from a script you provide. Not reliable outside that script, and it should not make refund or account decisions on its own.
Good for triaging log lines and alerts into plain English summaries so a person can prioritise faster. Not a substitute for a real detection pipeline, and it should never auto close an alert on its own.
Good for a fast, on-device assistant for short replies and simple instructions. Too small for long documents or complex reasoning, and it will make things up under pressure.
Good for summarising general contracts and explaining common UK legal terms in plain English. Has no specialist UK legal training, so treat it as a starting point only, never as legal advice, and confirm with a solicitor.
Good for a quick first read of US style contracts and flagging clauses worth a closer look. Has no specialist US legal training, so it is not a substitute for a licensed attorney and should not be used for filings.
Good for explaining accounting terms and drafting first pass budget summaries from numbers you provide. Has no professional finance training, so do not use it for tax filings or investment decisions without a qualified accountant.