tensorflow-cpu
TensorFlow is an open source machine learning framework for everyone.
Decision gist · record as of 2026-08-14
Yes, if you need a machine learning framework for CPU-based work. TensorFlow CPU is production-stable, actively maintained, and permissively licensed. The 20 runtime dependencies add moderate install friction, but the ecosystem is mature and well-tested. Choose this over the GPU variant only if you lack GPU hardware or need simpler deployment; for performance-critical training, GPU acceleration is typically necessary.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python >=3.10; 20 runtime dependencies (numpy, keras, protobuf, grpcio, h5py, and others) must resolve cleanly in your environment.
- Medium install friction due to 20 runtime dependencies and wheel-based distribution across multiple Python versions (3.10–3.13) and platforms.
- Active maintenance with recent commits and strong community backing (197028 stars) suggests reliable ongoing support.
License · maintenance · safety
Apache 2.0 (permissive) — Apache 2.0 permissive license allows commercial and private use with minimal restrictions, making it suitable for most projects that can accommodate attribution and license inclusion.
last release 2026-03-06 (161 days) · last repo commit 2026-08-14 · 197,028 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 1,837,518 downloads/mo, #3,500 on PyPI
Alternatives
Verify before relying
pip install tensorflow-cpu==2.21.0
import tensorflow as tf
model = tf.keras.Sequential([tf.keras.layers.Dense(10)])- Whether the CPU variant is suitable for your model size and training throughput requirements compared to GPU variants.
- Compatibility of all 20 runtime dependencies in your specific Python environment and OS version.
What it is and what it does
TensorFlow CPU is an open-source machine learning framework designed for numerical computation and deep learning on CPU-based hardware. It provides a flexible architecture for building, training, and deploying models across desktops and servers, with a core API built around tensor operations and automatic differentiation. The package includes Keras as a high-level API for model construction and comes with support for scientific computing beyond machine learning.
The CPU variant trades GPU acceleration for simpler deployment and lower system requirements. It brings 20 runtime dependencies including numpy for array operations, keras for model building, protobuf for serialization, grpcio for distributed computing, and h5py for model persistence. Installation is straightforward via wheel distribution, though the dependency chain adds moderate friction. Active maintenance and widespread adoption make it a stable choice for learning, prototyping, and production inference on CPU systems.
Use it for
- Train neural networks and deep learning models on CPU systems without GPU hardware.
- Build and deploy machine learning models for inference on edge devices or servers.
- Perform numerical computation and tensor operations for scientific research.
- Prototype machine learning workflows before scaling to GPU or TPU infrastructure.
- Develop and test models in environments where GPU drivers or CUDA are unavailable.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you need a machine learning framework for CPU-based work.
TensorFlow CPU is production-stable, actively maintained, and permissively licensed. The 20 runtime dependencies add moderate install friction, but the ecosystem is mature and well-tested. Choose this over the GPU variant only if you lack GPU hardware or need simpler deployment; for performance-critical training, GPU acceleration is typically necessary.
Install
tensorflow-cpu on PyPI
Before you install
Medium install friction due to 20 runtime dependencies and wheel-based distribution across multiple Python versions (3.10–3.13) and platforms. Active maintenance with recent commits and strong community backing (197028 stars) suggests reliable ongoing support.
Requires Python >=3.10; 20 runtime dependencies (numpy, keras, protobuf, grpcio, h5py, and others) must resolve cleanly in your environment.
License in practice
Apache 2.0 permissive license allows commercial and private use with minimal restrictions, making it suitable for most projects that can accommodate attribution and license inclusion.
Quickstart
pip install tensorflow-cpu==2.21.0
import tensorflow as tf
model = tf.keras.Sequential([tf.keras.layers.Dense(10)])Verify before relying
- Whether the CPU variant is suitable for your model size and training throughput requirements compared to GPU variants.
- Compatibility of all 20 runtime dependencies in your specific Python environment and OS version.
Package facts
| License | Apache 2.0 permissive |
| Python support | Supports the current Python release >=3.10 |
| Install friction | Medium. Platform-specific wheel |
| Runtime dependencies | 20 packagesabsl-pyastunparseflatbuffersgastgoogle_pastalibclangopt_einsumpackagingprotobufrequestssetuptoolssixtermcolortyping_extensionswraptgrpciokerasnumpyh5pyml_dtypes |
| Maintenance | Actively maintained 161 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 1,837,518 / month, #3,500 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 5 - Production/StableEnvironment :: GPU :: NVIDIA CUDA :: 12Environment :: GPU :: NVIDIA CUDA :: 12 :: 12.2Intended Audience :: DevelopersIntended Audience :: EducationIntended Audience :: Science/ResearchLicense :: OSI Approved :: Apache Software LicenseProgramming Language :: Python :: 3Programming Language :: Python :: 3 :: OnlyProgramming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Topic :: Scientific/EngineeringTopic :: Scientific/Engineering :: Artificial IntelligenceTopic :: Scientific/Engineering :: MathematicsTopic :: Software DevelopmentTopic :: Software Development :: LibrariesTopic :: Software Development :: Libraries :: Python Modules |
Evidence: tensorflow_cpu-2.21.0-cp310-cp310-manylinux_2_27_x86_64.whl; tensorflow_cpu-2.21.0-cp310-cp310-win_amd64.whl; tensorflow_cpu-2.21.0-cp311-cp311-manylinux_2_27_x86_64.whl; tensorflow_cpu-2.21.0-cp311-cp311-win_amd64.whl; tensorflow_cpu-2.21.0-cp312-cp312-manylinux_2_27_x86_64.whl; tensorflow_cpu-2.21.0-cp312-cp312-win_amd64.whl; tensorflow_cpu-2.21.0-cp313-cp313-manylinux_2_27_x86_64.whl; tensorflow_cpu-2.21.0-cp313-cp313-win_amd64.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
An agent finds packages by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language. Give your agent the search over MCP.
More Software Development packages
Provides backported and experimental type hints for Python 3.9+, allowing use of newer typing features on older Python versions and enabling early experimentation with type system PEPs before they enter the standard library.
NumPy provides an N-dimensional array object and a comprehensive suite of mathematical, linear algebra, Fourier transform, and random number functions for scientific computing in Python.
FastAPI is a Python web framework for building REST APIs using type hints, with automatic request validation, serialization, and interactive API documentation.
Provides a way to document function parameters, class attributes, return types, and variables inline using Python's `Annotated` type hint syntax instead of traditional docstrings.
Typer builds command-line applications from Python functions using type hints, automatically generating help text, argument parsing, and shell completion.
Install it if you are building CLIs in Python.
Distlib provides low-level packaging utilities for building, distributing, and managing Python software—including metadata handling, version specifiers, wheel support, script installation, and dependency resolution.
See also tensorflow · tensorflow-cpu-aws · tensorflow-intel · tensorflow-aarch64 · tf-nightly-cpu · tf-nightly · tf-models-nightly · tensorly · thinc · paddlepaddle