Launching today

Splashboard

Launching today

A native Mac app for running local LLMs with Splash

0 followers

A native Mac app for running local LLMs with Splash

0 followers

Visit website

Splashboard is an open-source Mac app for Splash, Inco's fast local LLM engine for Apple silicon. It installs Splash and a model, then gives you chat with thinking, live tok/s, memory and prompt-cache stats, every serve option with presets for your Mac's memory, and Claude Code, OpenCode or Codex in a built-in terminal pointed at your local model. 10 MB, Tauri + Rust, signed and notarized. No terminal needed. Not affiliated with Inco.

Free

Launch tags:Open Source•Artificial Intelligence•GitHub

Launch Team

Render Sandboxes: a computer for every agentGive every agent its own machine. Starts in under a second

Promoted

Maker

📌

Hi Product Hunt! I built Splashboard because Splash, Inco's local LLM engine for Apple silicon, is fast but lives in the terminal. Splashboard installs it, downloads a model, and gives you chat, live speed and memory stats, launch settings for every serve flag, and coding agents (Claude Code, OpenCode, Codex) in a built-in terminal pointed at your local model. It's a 10 MB Tauri app, Apache-2.0, signed and notarized. Qwen3.8-27B runs at about 63 tok/s on my M3 Max. Not affiliated with Inco. I'd love feedback, especially from people on 16-32 GB Macs.

Report

1mo ago