edge-studio 0.0.1rc1

Edge Studio — on-device LLM optimization workbench for Apple Silicon

Edge Studio

Edge Studio is AtomGradient's local workbench for building and testing on-device AI products on Apple Silicon. It ships as a Python package with a local Studio UI, an API server, and CLI workflows for model preparation, local chat, and the Neural Imprint learning demo.

Start with the developer documentation when you are building an app or integrating the SDK:

• Developer site: https://atomgradient.github.io/edge-developers/

Install

Use Python 3.11 in an isolated environment before installing Edge Studio.

With venv:

python3.11 -m venv .venv
source .venv/bin/activate
python -m pip install --upgrade pip
python -m pip install edge-studio

With uv:

uv venv --python 3.11 .venv
source .venv/bin/activate
uv pip install edge-studio

Current release candidate: 0.0.1rc1.

For a deterministic RC install:

python -m pip install edge-studio==0.0.1rc1

The package installs one command-line entry point:

Command	Use
edge	Launch Studio, prepare models, run local chat, inspect receipts, and try the learning demo.

Quick Start

python3.11 -m venv .venv
source .venv/bin/activate
python -m pip install edge-studio
edge studio
open http://127.0.0.1:18842

Edge Studio binds to 127.0.0.1:18842 by default. Override the host or port with VLM_HOST and VLM_PORT when you need a different local address.

First Model

The baseline developer-preview model is qwen3.5-9b-4bit.

edge models where qwen3.5-9b-4bit
edge models fetch qwen3.5-9b-4bit --source auto

edge models fetch supports ModelScope, Hugging Face, and hf-mirror sources. The auto mode chooses a source order from the local network environment.

First Chat

Run a local multi-turn chat after the model is available:

edge demo chat --model qwen3.5-9b-4bit --interactive

The first 9B model load can take tens of seconds. After [chat:ready], ask a few questions and exit with /exit.

Learning Demo

Run the local correction-learning demo once the baseline model is ready:

edge demo learn run --model qwen3.5-9b-4bit

The demo exercises local receipts, correction capture, Neural Imprint artifact generation, and a follow-up query without bundling internal evaluation data.

For the full walkthrough, SDK integration paths, and API references, use the Edge Developers documentation:

• https://atomgradient.github.io/edge-developers/docs/overview

Source Install

Use the source path when contributing to Edge Studio or testing a local checkout:

git clone https://github.com/AtomGradient/edge-studio.git
cd edge-studio
python3.11 -m venv .venv
source .venv/bin/activate
python -m pip install --upgrade pip
python -m pip install -e ".[dev]"

Launch the packaged UI/API server from the source checkout:

edge studio
open http://127.0.0.1:18842

For frontend development, run Vite separately and keep the backend server running:

npm --prefix frontend ci
npm --prefix frontend run dev
edge studio

The Vite UI runs at http://localhost:5173; the backend stays on http://127.0.0.1:18842.

Build a Wheel

python -m pip install --upgrade build
./scripts/build_wheel.sh

The build script compiles the frontend and copies frontend/dist into package resources before building the wheel, so users installing the wheel do not need Node.js.

Release Checks

python -m pytest tests -q
npm --prefix frontend run lint
npm --prefix frontend run build
python -m build

License

Edge Studio is released under the MIT License. See LICENSE.