--- title: "nni vs PocketFlow" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/microsoft-nni-vs-tencent-pocketflow" tools: ["microsoft-nni", "tencent-pocketflow"] --- # nni vs PocketFlow *GraphCanon updated Aug 4, 2026* ## Verdict Pick nni if nNI is an AutoML toolkit that supports feature engineering, neural architecture search, model compression, and hyperparameter tuning with the flexibility of Python programming; pick PocketFlow if pocketFlow automates deep learning model compression to enhance inference efficiency with minimal human effort by selecting optimal hyper-parameters for model development focusing on mobile applications. [nni](https://nni.readthedocs.io) reports 14k GitHub stars, 1.9k forks, and 415 open issues, last pushed Jul 3, 2024. [PocketFlow](https://pocketflow.github.io) has 2.9k stars, 491 forks, and 75 open issues, last pushed Mar 31, 2023. Figures are from public GitHub metadata via [nni's repository](https://github.com/microsoft/nni) and [PocketFlow's repository](https://github.com/Tencent/PocketFlow). | | [nni](/tools/microsoft-nni.md) | [PocketFlow](/tools/tencent-pocketflow.md) | | --- | --- | --- | | Tagline | An open source AutoML toolkit for automating machine learning lifecycle | An Automatic Model Compression framework for developing smaller and faster AI applications | | Stars | 14,363 | 2,909 | | Forks | 1,853 | 491 | | Open issues | 415 | 75 | | Language | Python | Python | | Adopt for | NNI is an AutoML toolkit that supports feature engineering, neural architecture search, model compression, and hyperparameter tuning with the flexibility of Python programming. | PocketFlow automates deep learning model compression to enhance inference efficiency with minimal human effort by selecting optimal hyper-parameters for model development focusing on mobile applications. | | Persona | - | - | | Runtime | - | - | | License | MIT | Other | | Categories | Model Training | Inference & Serving, Model Training | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [nni](/tools/microsoft-nni.md) | [PocketFlow](/tools/tencent-pocketflow.md) | | --- | --- | --- | | Maintenance | Archived (8%) | Dormant (18%) | | Days since push | 762d | 1221d | | Archived on GitHub | Yes | No | | Open issues (now) | 415 | 75 | | Full report | [trust report](/tools/microsoft-nni/trust.md) | [trust report](/tools/tencent-pocketflow/trust.md) | ## Decision facts: nni - **Adopt for:** NNI is an AutoML toolkit that supports feature engineering, neural architecture search, model compression, and hyperparameter tuning with the flexibility of Python programming. ## Decision facts: PocketFlow - **Adopt for:** PocketFlow automates deep learning model compression to enhance inference efficiency with minimal human effort by selecting optimal hyper-parameters for model development focusing on mobile applications. ## Choose when ### Choose nni if… - License: nni is MIT, PocketFlow is Other. - Tags unique to nni: automated-machine-learning, bayesian-optimization, data-science, deep-neural-network. - nni ships Docker support for self-hosted deployment. - You need to automate extensive parts of your machine learning lifecycle from preprocessing to deployment. ### Choose PocketFlow if… - License: PocketFlow is Other, nni is MIT. - Tags unique to PocketFlow: computer-vision, mobile-app, model-compression. - Also covers Inference & Serving. - When you need to optimize TensorFlow models specifically for deployment on devices with limited computational resources like mobile phones ## When NOT to use nni - You require real-time automated tuning capabilities, as NNI focuses on batch processing and model training scenarios. - If your project demands direct integration with specific deep learning frameworks beyond PyTorch and TensorFlow, NNI support is limited to these two environments. ## When NOT to use PocketFlow - Avoid if your project does not require model compression and efficiency improvement for deployment - Do not use if the TensorFlow-centric tools are irrelevant to your project, as PocketFlow integrates closely with TensorFlow APIs ## Common questions ### What is the difference between nni and PocketFlow? nni: An open source AutoML toolkit for automating machine learning lifecycle. PocketFlow: An Automatic Model Compression framework for developing smaller and faster AI applications. See the comparison table for live GitHub stats and shared categories. ### When should I choose nni over PocketFlow? Choose nni over PocketFlow when License: nni is MIT, PocketFlow is Other; Tags unique to nni: automated-machine-learning, bayesian-optimization, data-science, deep-neural-network; nni ships Docker support for self-hosted deployment; You need to automate extensive parts of your machine learning lifecycle from preprocessing to deployment. ### When should I choose PocketFlow over nni? Choose PocketFlow over nni when License: PocketFlow is Other, nni is MIT; Tags unique to PocketFlow: computer-vision, mobile-app, model-compression; Also covers Inference & Serving; When you need to optimize TensorFlow models specifically for deployment on devices with limited computational resources like mobile phones. ### When should I avoid nni? You require real-time automated tuning capabilities, as NNI focuses on batch processing and model training scenarios. If your project demands direct integration with specific deep learning frameworks beyond PyTorch and TensorFlow, NNI support is limited to these two environments. ### When should I avoid PocketFlow? Avoid if your project does not require model compression and efficiency improvement for deployment Do not use if the TensorFlow-centric tools are irrelevant to your project, as PocketFlow integrates closely with TensorFlow APIs ### Is nni or PocketFlow more popular on GitHub? nni has more GitHub stars (14,363 vs 2,909). Stars measure visibility, not whether either tool fits your constraints. ### Are nni and PocketFlow open source? Yes - both are open-source projects on GitHub (nni: MIT, PocketFlow: Other). ### Where can I find alternatives to nni or PocketFlow? GraphCanon lists graph-backed alternatives at [nni alternatives](/tools/microsoft-nni/alternatives) and [PocketFlow alternatives](/tools/tencent-pocketflow/alternatives) ([nni markdown twin](/tools/microsoft-nni/alternatives.md), [PocketFlow markdown twin](/tools/tencent-pocketflow/alternatives.md)), ranked by typed relationship edges rather than popularity votes. ### Is there a machine-readable version of this comparison? Yes. The markdown twin at [this comparison](/compare/microsoft-nni-vs-tencent-pocketflow.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, nni or PocketFlow? nni: Archived. PocketFlow: Dormant. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance. ### Where are the full trust reports for nni and PocketFlow? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [nni trust report](/tools/microsoft-nni/trust); [PocketFlow trust report](/tools/tencent-pocketflow/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=microsoft-nni`](/api/graphcanon/graph?tool=microsoft-nni) - LLM index: [/llms.txt](/llms.txt) - Full corpus: [/llms-full.txt](/llms-full.txt) _GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_