Kronos is the first open-source foundation model for financial candlesticks (K-lines), trained on data from over 45 global exchanges. It is designed to handle the unique, high-noise characteristics of financial data. Kronos is a family of decoder-only foundation models, pre-trained specifically for the "language" of financial markets—K-line sequences. It leverages a novel two-stage framework: 1. A specialized tokenizer first quantizes continuous, multi-dimensional K-line data (OHLCV) into hierarchical discrete tokens. 2. A large, autoregressive Transformer is then pre-trained on these tokens, enabling it to serve as a unified model for diverse quantitative tasks. The success of large-scale…
Open-weight model · Time series forecasting
Kronos-Tokenizer-2k
by ShiYu NeoQuasar/Kronos-Tokenizer-2k
Kronos is the first open-source foundation model for financial candlesticks (K-lines), trained on data from over 45 global exchanges. It is designed to handle the unique, high-noise characteristics of financial data.
Parameters4M
Context—
Weights15.8 MB
Licensemit
AccessOpen weights
Monthly Downloads437.2k
Runs On
What it takes to serve Kronos-Tokenizer-2k (4M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits |
|---|---|---|---|---|---|
| 16-bit | 0.0 GB | 0.0 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.0 GB | 0.0 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.0 GB | 0.0 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Sep 18, 2026.
SAVRN's Notes on Kronos-Tokenizer-2k
What do you run on a model whose memory line reads 0.0 GB at all three precisions? Whatever is already in the rack. Kronos-Tokenizer-2k sits at the front of the Kronos framework, quantizing continuous OHLCV candlestick data into hierarchical discrete tokens for the autoregressive Transformer that follows. At 4 million parameters and about 16 MB across 4 files, it is a preprocessing step, not a workload; the cheapest setup we price, one MI300X with 192 GB at $1.85 an hour, is waste unless the forecasting model rides on the same card.
MIT is about as light as licensing gets: commercial use, modification and redistribution, with only the copyright and permission notices to carry along. A tokenizer does nothing alone, so confirm which Kronos forecasting model you will pair it with, read arXiv:2508.02739 for the two-stage design, and note the September 9, 2025 update against a July 1, 2025 release.
Model Card
By ShiYu, published under mit, revision 26966d003506.
Kronos: A Foundation Model for the Language of Financial Markets
Kronos is the first open-source foundation model for financial candlesticks (K-lines), trained on data from over 45 global exchanges. It is designed to handle the unique, high-noise characteristics of financial data.
Introduction
Kronos is a family of decoder-only foundation models, pre-trained specifically for the "language" of financial markets—K-line sequences. It leverages a novel two-stage framework: 1. A specialized tokenizer first quantizes continuous, multi-dimensional K-line data (OHLCV) into hierarchical discrete tokens. 2. A large, autoregressive Transformer is then pre-trained on these tokens, enabling it to serve as a unified model for diverse quantitative tasks.
Identity and Version
- Repository
- NeoQuasar/Kronos-Tokenizer-2k
- Publisher
- ShiYu
- Task
- Time series forecasting
- Modality
- Time series
- Library
- torch
- Parameters
- 4M parameters
- Languages
- Not stated by the source
- Revision
- 26966d0035065a0cae0ebad7af8ece35bc1fb51c
- First published
- 2025-07-01
- Last updated
- 2025-09-09
Files and Weights
4 files, 15.9 MB in total. The weights are 1 file totalling 15.8 MB in safetensors.
Weights1 file · 15.8 MB
Configuration1 file · 301 B
Documentation1 file · 8.9 KB
Repository1 file · 1.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 15.8 MB | b97ec46b3b72 |
| config.json | Configuration | 301 B | — |
| README.md | Documentation | 8.9 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- mit
- Access
- Open weights, no gate
- Download size
- 15.8 MB
Download from ShiYu
Released by ShiYu through its official repository on Hugging Face. Read the license.
Built From
- Described by arXiv:2508.02739
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 15.8 MB |
| 16-bit | 0.0 GB |
| 8-bit | 0.0 GB |
| 4-bit | 0.0 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Compare Kronos-Tokenizer-2k
Questions About Kronos-Tokenizer-2k
How much GPU memory does Kronos-Tokenizer-2k need?
About 0 GB at 16-bit and 0 GB at 4-bit: the weights (4M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run Kronos-Tokenizer-2k on?
At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Can I use Kronos-Tokenizer-2k commercially?
Yes. Kronos-Tokenizer-2k is released under MIT License. The MIT License is a short permissive license. It permits commercial use, modification and redistribution, provided the copyright notice and permission notice are included.
Similar Models
Kronos is the first open-source foundation model for financial candlesticks (K-lines), trained on data from over 45 global exchanges. It is designed to handle the unique, high-noise characteristics of financial data. Kronos is a family of decoder-only foundation models, pre-trained specifically for the "language" of financial markets—K-line sequences. It leverages a novel two-stage framework: 1. A specialized tokenizer first quantizes continuous, multi-dimensional K-line data (OHLCV) into hierarchical discrete tokens. 2. A large, autoregressive Transformer is then pre-trained on these tokens, enabling it to serve as a unified model for diverse quantitative tasks. The success of large-scale…
Toto (Time Series Optimized Transformer for Observability) is a family of time series foundation models for multivariate forecasting developed by Datadog. Toto 2.0 is the current generation, featuring u-μP-scaled transformers ranging from 4m to 2.5B parameters, all trained from a single recipe. Forecast quality improves reliably with parameter count across the family. The family sets a new state of the art on three forecasting benchmarks: BOOM, our observability benchmark; GIFT-Eval, the standard general-purpose benchmark; and the recent contamination-resistant TIME benchmark. Inference code is available on GitHub. For more examples, see the Quick Start notebook and GluonTS integration…
Building on top of TTM-R1 and TTM-R2, we introduce the next generation of TinyTimeMixer under the Granite time-series foundation model family — Granite-TTM-R3. This release incorporates several novel tiny-neural architectural innovations designed to push the limits of accuracy in high-speed forecasting, a critical requirement for real-world production deployments. Granite-TTM-R3 is a family of pretrained models supporting multiple real-world forecasting scenarios: - Zero-shot forecasting across unseen datasets - Few-shot adaptation effective with as few as ~1K samples - Full fine-tuning for domain-specific optimization - Multivariate time-series forecasting - Exogenous / control variable…
TinyTimeMixers (TTMs) are compact pre-trained models for Multivariate Time-Series Forecasting, open-sourced by IBM Research. With model sizes starting from 1M params, TTM introduces the notion of the first-ever “tiny” pre-trained models for Time-Series Forecasting. The paper describing TTM was accepted at NeurIPS 24. TTM outperforms other models demanding billions of parameters in several popular zero-shot and few-shot forecasting benchmarks. TTMs are lightweight forecasters, pre-trained on publicly available time series data with various augmentations. TTM provides state-of-the-art zero-shot forecasts and can easily be fine-tuned for multi-variate forecasts with just 5% of the training…
TinyTimeMixers (TTMs) are compact pre-trained models for Multivariate Time-Series Forecasting, open-sourced by IBM Research. With less than 1 Million parameters, TTM (accepted in NeurIPS 24) introduces the notion of the first-ever “tiny” pre-trained models for Time-Series Forecasting. TTM outperforms several popular benchmarks demanding billions of parameters in zero-shot and few-shot forecasting. TTMs are lightweight forecasters, pre-trained on publicly available time series data with various augmentations. TTM provides state-of-the-art zero-shot forecasts and can easily be fine-tuned for multi-variate forecasts with just 5% of the training data to be competitive. Refer to our paper for…