The most efficient and usable model of PorchLM as of the 30th of July, 2026. More sophisticated than all of the previous versions. Trained on 3 billion tokens. It is a 50M parameter model, which is a good balance between performance and efficiency.
An experimental model of PorchLM trained on 40 billion tokens. More efficient than V4, V2, and V1, but still not recommended for production use. Designed for testing and development purposes.
A very good model of PorchLM. It's larger than the last model with 50 million parameters, providing improved performance and accuracy over the previous version.