First LLM Studio
A local-first workbench for Apple Silicon that brings agent sessions, model comparison, fine-tuning, benchmarking and runtime monitoring for local MLX and remote language models into one interface.
First LLM Studio is a local-first workbench for large language model work on Apple Silicon, built around local MLX runtimes as well as remote API targets. It is positioned against a plain chat interface, aimed instead at people who need to compare model behavior side by side, debug a runtime, run evaluations, prepare fine-tuning adapters and keep local and remote model work inside one product.
Its surfaces include tool-enabled agent sessions with target selection, runtime state and trace review; a route for composing prompts and comparing several models' output in parallel lanes; a fine-tune studio covering datasets, training recipes, evaluation and export; model discovery; and administrative monitoring, including runtime recovery and release evidence tracking.
It is built with TypeScript and Next.js, and its interface is available in English and Simplified Chinese.