#44th of 5 in Open models
kronos
Pretrained decoder-only models that forecast financial candlestick (K-line) series
- Stars
- 40.8k
- License
- MIT
- Last commit
- Apr 2026
- Language
- Python
11,066 on 25 Mar 202640,752 on 14 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Kronos is a family of decoder-only Transformers pretrained on OHLCV candlestick data from over 45 exchanges. A tokenizer quantizes K-lines into hierarchical discrete tokens, and the model forecasts future bars through a KronosPredictor class with temperature and top-p sampling. Weights for mini, small and base are on Hugging Face, and the repo includes a Qlib-based fine-tuning and backtest pipeline.
Who it is for: Quant researchers and ML engineers forecasting candlestick time series
Strengths
- Open weights at 4.1M, 24.7M and 102.3M params on Hugging Face
- Few-line predict and predict_batch API returning pandas DataFrames
- Includes tokenizer and predictor fine-tuning scripts with a Qlib backtest example
- MIT license; paper accepted at AAAI 2026
Weaknesses
- Kronos-large (499.2M) weights are not released
- Context limited to 512 tokens, except 2048 for Kronos-mini
- Batch prediction requires identical lookback and pred_len across all series
- Fine-tuning example is a demo, not a production trading system; no releases tagged
What it needs
- GPU optional
- Needs PyTorch, Hugging Face Hub, pyqlib (fine-tuning only), Comet.ml (optional)
- Models: Kronos-mini, Kronos-small, Kronos-base, Hugging Face
Head to head
Also in Open models
See all 5| Rank | Project | Score |
|---|---|---|
| 1 | llmfitRust tool that checks which LLMs fit your RAM, CPU and GPU | 80 out of 100 |
| 2 | layaSingle-pass multilingual classifier for typed choice, score and yes/no decisions | 67 out of 100 |
| 3 | timesfmPretrained time-series foundation model for zero-shot forecasting from Google Research | 65 out of 100 |
| #5 | clipOpenAI's reference PyTorch code and weights for contrastive image-text embeddings | 29 out of 100 |