N

Kronos Mini

Model directory
NeoQuasar/Kronos-mini

4.1M params | MIT | Upstream checkpoint

Kronos Mini is the smallest checkpoint in the NeoQuasar Kronos family — a tokenizer-based time-series foundation model purpose-built for financial OHLCV candlestick data. At 4.1M parameters it is the most lightweight way to access the Kronos design, the entry point to the family for cost- and latency-sensitive financial forecasting.

Architecturally Kronos treats forecasting like a language-modeling problem over price action: a custom tokenizer discretizes price movements into a vocabulary, and a GPT-style decoder autoregressively predicts future candlestick patterns. The Mini variant uses a 2K-token vocabulary and a 2048-token context window. Across the family, the official Kronos model cards describe pretraining on over 12B K-line records from 45 global exchanges, which is what gives the checkpoints their broad zero-shot coverage of market data.

Where to run this model

Compute availability, hardware requirements, and pricing depend on the execution provider.

Hugging Face · Weights & deployment

Get model weights, deployment instructions, and current provider listings.

  • sktime TServe

    self-hosted runtime · Family / provider variant · Source checked 2026-10-06

    Run a model-serving container on your own hardware or compute account. Select the catalog checkpoint and matching runtime image.

Hugging Face provider mappings checked 2026-10-06. No Inference Provider mapping was listed for this checkpoint.

Model Classification

Family

Kronos

Type

time series foundation model

Pretrained time-series model for zero-shot or few-shot forecasting workloads.

Training Data

Official Kronos model cards describe pretraining on over 12B K-line records from 45 global exchanges.

Recommended For

  • • Financial time-series forecasting with OHLCV candlestick data
  • • Multi-asset price prediction across equities, forex, and crypto

Strengths

  • • Purpose-built tokenizer for financial price movement patterns
  • • Native OHLCV support with synthetic fallback for univariate series

Limitations

  • • Domain-specific to financial data — not a general-purpose TSFM
  • • Best fit when open, high, low, and close covariates are provided explicitly; the univariate fallback is a compatibility path, not the ideal contract
  • • Limited public documentation and benchmark coverage compared to major TSFM families

Capabilities

forecastingzero-shot

Tags

neoquasarkronosfinancialohlcvlightweight

Specifications

Parameters
4.1M
Architecture
GPT-style decoder with financial candlestick tokenizer (2K vocabulary)
Context length
n/a
Max context
n/a
Minimum history
n/a
Recommended history
n/a
Input step
n/a
Required target series
1
Temperature
Ignored
Top P
Ignored
Max output
n/a
License
MIT

Related models