google/flax

Health v2 · maintenance only

Adoption not part of the score

7303 stars · 830 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Flax is a neural network library and ecosystem for JAX designed for flexibility, featuring the newer NNX API with first-class Python reference semantics alongside the older Linen API. It is developed in close collaboration with the JAX team for high-performance deep learning research.

Use cases

• build neural networks in jax
• train deep learning models with jax
• define models with regular python objects and mutable state
• run deep learning research with flexible training loops
• migrate from flax linen to the nnx api
• train models on gpus and tpus

When to choose

• you use JAX and want a flexible, research-friendly neural network library
• you want Python reference semantics with mutable, shareable model state (NNX)
• you need a mature, Google-backed ecosystem with examples and tutorials

When to avoid

• you prefer PyTorch or TensorFlow-style frameworks
• you want a batteries-included high-level training framework with opinionated defaults
• your project depends on the legacy Linen API without plans to migrate

Facets

library · maturity active

machine-learning deep-learning llm-training machine-learning deep-learning artificial-intelligence python cross-platform jax neural-networks nnx linen research google gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="google/flax")