Arena
Race up to four models on the same prompt to compare speed and answer quality in LM Mini Arena.
Answer first
Arena runs the same prompt across multiple models at once so you can compare tokens/sec, time-to-first-token, and the written answers — then pick a default for chat or Personas.
Open Arena
- Phone: home ⋯ → Arena
- Mac Home: Arena in the nav rail (⌘4)
- Welcome wizard: skippable Find a model that fits (about a minute)
What you can race
Add contestants from this device, LM Studio, Ollama, oMLX, or cloud (cloud-in-Arena is a Pro capability in current builds). Free discovery focuses on multi-model speed races (up to four). Pro unlocks custom prompts, cloud contestants, and history where enabled.
Suggested lanes: this device vs desktop, “Race top 2”, Quick vs Full suite — pick what you have loaded.
How a race works
- Pick contestants and a prompt (or use the built-in discovery prompts)
- Start — streams run live with speed metrics
- Read answers, note TTFT / tok/s
- Optionally apply that model as your everyday default or Persona binding
Anonymous benchmarks
If you opt in via Settings, LM Mini can share anonymous race metrics. Off unless you enable the toggle.