A home for your models.
Download a recommendation, import a supported artifact, or link a model you already have. Give each one an API name and a profile that makes sense.
YOUR MODEL LIBRARY
SSwift 1.5Vision
OOrcaRouterText
HHereticCompact
LOCAL AI, MADE SIMPLE
Your GPU.
Your models.
Your workspace.
NInfer, made simple on Windows. NInferEZ Manager brings your models, engines, and local AI API together in one convenient app.
Get to know Manager ↗
NInferEZ ManagerYOUR WORKSPACE
Local firstEverything in one place.
Ready when you are.
Model libraryLocal files & linked models
GPU engineA package for your GPU
Your models NInfer v3
S
Swift 1.527B · NVFP4 · Text + Vision
VisionO
OrcaRouter27B · IQ3_XXS · MTP + DFlash2
Text127.0.0.1:8173/v1YOUR LOCAL APIA LIBRARY THAT IS YOURS
Your models. Organized.
Download, import, or link an existing file.
S
Swift 1.5NVFP4 · 21.22 GiB artifact
VisionO
OrcaRouterIQ3_XXS · 10.06 GiB artifact
TextO
OrcaRouterIQ3_XXS · 12.13 GiB artifact
TextManaged profiles help you choose a starting point for your model and available VRAM.
FROM SOURCE TO ARTIFACT
A guided conversion.
The same backend as the standalone Converter.
- 1Choose your sourceLocal checkpoint or supported GGUF
- 2Check compatibilityResources, geometry, and prepared plans
- 3Review & convertNative NInfer artifact, with progress
THE RIGHT ENGINE
Matched to your hardware.
Choose a package for your NVIDIA GPU.
RTX 3000Compatible architecture targets
sm86RTX 4000Compatible architecture targets
sm89RTX 5000Compatible architecture targets
sm120aSHA-256 integrity checks before activation.
Explore the workspace Interactive product illustration
BUILT FOR YOUR LOCAL AI
NVIDIA GPU engines
NInfer v3 models
OpenAI-compatible API
Guided conversion
MEET YOUR MANAGER
Less setup.
More possibilities.
From choosing a model to connecting your favorite client, Manager keeps the moving parts within reach.
Settings that work together.
Managed profiles adapt dependent controls to your model and engine. Go manual whenever you want more control.
Managed settings
Memory estimates include context headroom.
Your client. Your local API.
Connect an OpenAI-compatible app to Manager. Models load on demand and can unload after an adjustable idle period.
BASE URL
127.0.0.1:8173/v1The right engine, ready.
Download the GPU package that matches your hardware. Manager checks integrity before activating it.
Explore engine compatibilityConversion, without the detour.
Prepare supported checkpoints in Manager’s guided converter, or open up manual controls for advanced plans.
Meet the ConverterONE CONNECTED ECOSYSTEM
Start with Manager.
Go deeper when you need to.
A complete desktop experience, with independent tools for the way you like to work.
START HERE
NInferEZ Manager
The desktop workspace for models, inference profiles, GPU engines, API access, and conversion.
Explore Manager PREPARENInferEZ Converter
Turn supported checkpoints into NInfer artifacts with a guided wizard or detailed manual controls.
Explore Converter RUNNInferEZ Engine
Standalone serving, GPU-specific packages, and model inspection. The engine behind the experience.
Explore EngineMAKE IT YOURS
Three steps to local AI.
Get Manager.
Install it on Windows or extract the Portable ZIP into a writable folder.
Choose a download →Add your engine & model.
Select the package for your GPU, then download or link a supported NInfer artifact.
Find your model →Connect. Create. Repeat.
Point your AI client at the local API. Manager loads the selected model when you need it.
Connect a client →OUR MODEL COLLECTION
A model for your next idea.
Explore native NInfer conversions, with artifact details, component support, and original model cards.
SNVFP4
Swift 1.5
Qwen3.8 · 27B
A complete text and vision artifact, with native NVFP4 weights and a bundled speculative draft for compatible Blackwell GPUs.
TextVisionMTPDFlash2
21.22 GiBArtifact size
OIQ3_XXS
OrcaRouter
Qwen3.8 · 27B · DFlash2
Adds a DFlash2 draft to OrcaRouter, with MTP available as an alternative. Explore the published long-context measurements.
TextMTPDFlash2
12.13 GiBArtifact size
HIQ2_XS
Heretic
Qwen3.8 · 27B
Our smallest featured 27B artifact. A text-only IQ2_XS conversion for a more compact model library.
Text
7.84 GiBArtifact size
Explore all models →
Weights are downloaded separately. Each model keeps its own license.
A FEW THINGS TO KNOW
Good questions.
Clear answers.
More guidance in our getting started guide.
Open the guideWhat 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.
Can I use my existing AI client?
Yes. Connect an OpenAI-compatible client to http://127.0.0.1:8173/v1 and use the exact model API name shown in Manager. The API starts with Manager and loads a model when inference is requested.
Do my prompts leave my computer?
Inference through the default localhost API runs on your machine. Downloading models or engines and checking updates require network access. Your chosen client may have its own network behavior; optional LAN access must be enabled explicitly.
YOUR NEXT STEP
Put your GPU to work.
Your models, your workspace, your next idea.
Start with NInferEZ Manager.
Windows x64 · Installer or Portable