nowfound

Life & fun · October 14, 2026

T0: We trained a 256M SOTA open-weights time-series forecasting model

An open-weights time-series forecasting foundation model from The Forecasting Company. - theforecastingcompany/tfc-t0

T0: We trained a 256M SOTA open-weights time-series forecasting model launched on October 14, 2026 with 14 votes, #616 of 3,564 launches that month and more than 90% of that year's launches.

Visit github.com ↗Alternativestop 17% of October 2026

In plain words

T0 is an open-weights time-series forecasting model with 256 million parameters developed by The Forecasting Company. It is designed for users who need to predict future values in sequential data across various domains. The model stands out as a state-of-the-art foundation model that is freely available as open-source software, allowing developers and researchers to implement and customize it for their specific forecasting applications.

written from the facts on this page · October 2026

Does a similar job

all alternatives →
  • OpenAI Open Models2025 · openai.com · ▲480

    gpt-oss-120b and gpt-oss-20b open-weight language models

  • TensorFlow 1.02017 · tensorflow.org · ▲823

    Open-source machine learning library by Google

  • TabPFN v2 – A SOTA foundation model for small tabular data2025 · nature.com · ▲153

    I am excited to announce the release of TabPFN v2, a tabular foundation model that delivers state-of-the-art predictions on small datasets in just 2.8 seconds for classification and 4.8 seconds for regression compared to strong baselines tuned for 4 hours. Published in Nature, this model outperforms traditional methods on datasets with up to 10,000 samples and 500 features. The model is available under an open license: a derivative of the Apache 2 license with a single modification, adding an enhanced attribution requirement inspired by the Llama 3 license:…

  • Are You in the Weights?Jun 2026 · intheweights.com · ▲471

    With more traffic moving off-web and into LLMs, I got curious about what traces we leave "in the weights". My design partner and I built a site in the past few weeks that checks recognition across frontier and small models. It queries many of them in parallel, clusters the responses, and tells you how strongly they recognize you. Happy to answer any questions here!

  • A high-performance TensorFlow library for quantitative finance2021 · github.com · ▲153

    High-performance TensorFlow library for quantitative finance. - google/tf-quant-finance

  • Dream 7B2025 · hkunlp.github.io · ▲191

    Powerful Open Diffusion LLM, Beyond Autoregressive

More life & fun this month

the category →

Launched alongside, October 2026

the whole month →