NVIDIA ModelOpt

Open source

Library for model compression via quantization, pruning, distillation, and sparsity.

License: open-source
Open source: Yes

Editorial review

NVIDIA ModelOpt has not yet been editorially reviewed. User reviews and published field data below are unaffected — we say so rather than implying an editorial verdict.

Facts & attributes

Every value carries its evidence state. “—” means unknown — never a silent default (P-02).

Identity · Taxonomy

Documentation(HTTPS URL): https://nvidia.github.io/Model-Optimizer/Verified
Tags(open-source;cloud-native): quantization, distillation, pruning, TensorRT, inference optimizationVerified

Platform · Deployment

Delivery model(SaaS;self-hosted;desktop;mobile;embedded;managed-cloud;appliance): self-hostedVerification pending

Pricing · Licensing

License model(proprietary;open-source;source-available;dual-license): open-sourceVerification pending
Source repository(HTTPS URL): https://github.com/NVIDIA/TensorRT-Model-OptimizerVerified
SPDX license IDs(Apache-2.0;MIT): Apache-2.0Verified

Features · Product · Fit

Core capabilities(authoring;automation;analytics): Quantization, Distillation, Pruning, Neural architecture search, Speculative decoding, SparsityVerified

Audience · Use · Case

Best for(Neutral editorial summary): ML engineers compressing models for fast TensorRT-LLM, TensorRT and vLLM inferenceVerification pending
Primary use cases(build;monitor;automate): Compressing deep learning models for TensorRT-LLM, TensorRT and vLLM deployment, Optimizing inference speedVerification pending
Skill level(beginner;intermediate;advanced;specialist): advancedVerified

Lifecycle · Versioning

Maintenance status(active;maintenance;deprecated;EOL;archived): activeVerification pending

Vendor · Maintainer

Founded year(2012): 1993Verified
Headquarters country(US): United StatesVerified
Vendor type(commercial;foundation;community;government;consortium;individual): commercialVerification pending

User reviews

Review policy

No published reviews yet.