Open‑source engine runs Gemma 4 26B model on M‑series Macs using just 2 GB RAM

A new open‑source engine has been released on GitHub. It can execute the Gemma 4 26B large language model. The engine

A new open‑source engine has been released on GitHub. It can execute the Gemma 4 26B large language model. The engine requires only 2 GB of RAM. It is compatible with any Apple M‑series Mac. The project targets developers needing lightweight inference. The code is publicly available for review and contribution. Early benchmarks show the model runs without GPU acceleration. The repository invites community testing and improvement.