NInferEZby 2beng2
GET NINFEREZ MANAGER

Your local AI journey
starts here.

Manager 1.0.0. Choose the setup that fits your workflow.
The same Manager, whether you install it or take it with you.

RECOMMENDED

Windows installer

A familiar setup with shortcuts for your Windows account. The easiest place to start.

Version
1.0.0
Platform
Windows x64
Package size
203.1 MiB approximately
Download installer.exe · Per-user installationDownload SHA-256 checksums ↓
TAKE IT WITH YOU

Portable ZIP

Everything in one folder. Extract the full ZIP to a writable location and launch Manager.

Version
1.0.0
Platform
Windows x64
Package size
297.9 MiB approximately
Download Portable.zip · No installer neededDownload SHA-256 checksums ↓

The public release includes its application runtime. GPU engine packages and model weights are separate downloads. Releases are unsigned; Windows may show a publisher warning.

WHAT COMES NEXT

Get from download to first request.

01

Open Manager.

Finish setup or extract the complete Portable archive. Do not run an executable from inside a ZIP.

02

Add the essentials.

Download your GPU engine from Engine, then choose a model from Models or link your existing artifact.

LOOKING FOR THE OTHER TOOLS?

Go standalone.

Manager is the easiest starting point. The Converter and Engine also work independently.

NInferEZ ConverterGuided & manual model conversion
NInferEZ EngineServing packages for your NVIDIA GPU
BEFORE YOU DOWNLOAD

A few useful answers.

What do I need to get started?

Windows x64, a compatible NVIDIA GPU and driver, and enough VRAM for the model and context you choose. Install Manager, download the matching engine, and add a supported NInfer model. Model weights and GPU engines are separate downloads.

Installer or Portable: which should I choose?

The installer sets up Manager and shortcuts for your Windows account. Portable keeps the application and its data together: extract the entire ZIP into a writable folder, then run NInferEZ Manager.exe. Both offer the same Manager features.

Are all RTX cards tested?

Engine packages target compatible Ampere (sm86), Ada (sm89), and Blackwell (sm120a) GPUs. Published measurements are from RTX 5090. Other combinations remain Community Preview, and native NVFP4 weights require a compatible Blackwell target.