OpenTSLM TeeMoE

OpenTSLM TeeMoE is part of the OpenTSLM project. It brings numerical forecasting, context-conditioned forecasting, and time-series analysis together in one language model. Built on Qwen3.6-27B, it combines three LoRA experts through a learned controller that weights them for each request.

A single TeeMoE checkpoint simultaneously ranks in the top three on Context is Key, TimeSeriesExam, and GIFT-Eval in the paper's September 25, 2026 benchmark comparison.

Paper

The model is described in OpenTSLM TeeMoE: A Unified Time-Series Language Model for Forecasting, Contextual Prediction, and Reasoning.

Accepted at the Foundation Models for Temporal Systems (FMTS) workshop at NeurIPS 2026.

Paper · Code

Usage

See the TeeMoE repository for installation, evaluation, and training instructions.

The inference setup targets Linux with an NVIDIA 80 GB GPU. It requires Git, uv, the CUDA toolkit (nvcc), and a C++ compiler. The setup script creates the Python 3.12 environments:

git clone https://github.com/OpenTSLM/OpenTSLM-TeeMoE
cd OpenTSLM-TeeMoE
bash scripts/setup.sh inference
source .venv/bin/activate

Load this checkpoint through the TeeMoE package:

import numpy as np
from teemoe import TeeMoE

model = TeeMoE.from_pretrained("OpenTSLM/TeeMoE")
history = (10 + np.sin(np.arange(168) / 12)).tolist()

forecast = model.forecast(
    history,
    horizon=24,
    frequency="h",
    start="2024-05-01 00:00",
    context="A promotion starts at the first forecast hour and lasts 24 hours.",
)
print(forecast.median)
print(forecast.quantiles.shape)  # (24, 9), quantile levels 0.1 through 0.9

answer = model.analyze(
    history,
    "Which pattern best describes the series?",
    options=["Periodic variation", "Constant values", "Steady increase"],
)
print(answer.text)

from_pretrained also accepts a local directory. forecast_batch and analyze_batch accept lists of requests. See the code README for multi-GPU configuration, evaluation commands, and training from public data.

This checkpoint contains the three LoRA adapters, expert controller, numerical connector and decoder, and learned ensemble weights. The package downloads the base language model and external forecasting models as needed.

Citation

If you use TeeMoE in your work, please cite:

@misc{chen2026opentslmteemoe,
  title = {{OpenTSLM TeeMoE: A Unified Time-Series Language Model for Forecasting, Contextual Prediction, and Reasoning}},
  author = {Tony Chen and Timo Stoffregen and Maxwell Xu and Thomas Kaar and Martin Maritsch and Geremia Pompei and Nicolas Zumarraga and Robert Jakob and Paul Schmiedmayer and Patrick Langer and Juncheng Liu},
  year = {2026},
  eprint = {2609.40265},
  archivePrefix = {arXiv},
  primaryClass = {cs.LG},
  url = {https://arxiv.org/abs/2609.40265}
}

License

The TeeMoE components are released under the MIT license. The Qwen backbone and external forecasting models retain their respective licenses.