tinygrad

Plans and prices

Every plan, in full

On the record

Accelerators

Listed accelerators include OpenCL, CPU, Metal, CUDA, AMD, NV, Qualcomm, and WebGPU.github.com · read 7 Oct 2026

Autodiff

The project supports forward and backward passes with autodiff.tinygrad.org · read 7 Oct 2026

Community support

The project directs development discussion to GitHub and Discord.tinygrad.org · read 7 Oct 2026

Installation

The project recommends installing from source and also documents installation with pip.github.com · read 7 Oct 2026

Integration

The project says tinygrad is used in openpilot to run its driving model on a Snapdragon 845 GPU.tinygrad.org · read 7 Oct 2026

Intended users

The project describes tinygrad as a framework for deep learning and neural network training.tinygrad.org · read 7 Oct 2026

JIT

tinygrad provides TinyJit to capture and replay kernels in a decorated function.github.com · read 7 Oct 2026

Lazy execution

Tensor operations are lazy and run when the tensor is realized.docs.tinygrad.org · read 7 Oct 2026

License

The GitHub repository identifies the project license as MIT.github.com · read 7 Oct 2026

Maturity

The documentation says tinygrad is not yet version 1.0, while noting its API has been stable for a while.docs.tinygrad.org · read 7 Oct 2026

Multi GPU

The documentation says tensors can be sharded across multiple GPUs.docs.tinygrad.org · read 7 Oct 2026

Neural networks

The library includes neural network classes, optimizers, and state load/save management.docs.tinygrad.org · read 7 Oct 2026

Performance caveat

The project FAQ says tinygrad is not yet faster than PyTorch for most use cases.tinygrad.org · read 7 Oct 2026

Purpose

tinygrad is an end-to-end deep learning stack with a tensor library, compiler, JIT, and tools for training.github.com · read 7 Oct 2026

Alternatives to tinygrad

Every alternative, ranked