metadata
license: mit
library_name: kronos-mlx
pipeline_tag: time-series-forecasting
tags:
- mlx
- apple-silicon
- finance
- kronos
- time-series
base_model: NeoQuasar/Kronos-small
Kronos-small (MLX)
Apple MLX port of NeoQuasar/Kronos-small — a 24.7M-parameter foundation model for financial K-line (candlestick) forecasting (AAAI 2026).
The architecture and weights are unchanged from the upstream PyTorch checkpoint. The only difference is that PyTorch-only buffer tensors (*.rotary.inv_freq, tokenizer.bsq.basis, tokenizer.bsq.group_codebook, …) have been pruned because the kronos-mlx package recomputes them from scratch in __init__.
Usage
pip install kronos-mlx
from kronos_mlx import Kronos, KronosTokenizer, KronosPredictor
tokenizer = KronosTokenizer.from_pretrained("gxcsoccer/kronos-mlx-tokenizer-base")
model = Kronos.from_pretrained("gxcsoccer/kronos-mlx-small")
predictor = KronosPredictor(model, tokenizer, max_context=512)
pred_df = predictor.predict(
df=x_df,
x_timestamp=x_timestamp,
y_timestamp=y_timestamp,
pred_len=120,
)
For 8-bit weight quantization (~70% memory reduction on Linear layers, modest quality loss):
model = Kronos.from_pretrained("gxcsoccer/kronos-mlx-small", bits=8)
Numerical parity
Bit-exact integer paths and float divergence within ~5e-5 (max) of the upstream PyTorch reference under identical inputs. See the parity test suite for the validation methodology.
Original
- Paper: AAAI 2026
- Upstream: shiyu-coder/Kronos
- PyTorch weights: NeoQuasar/Kronos-small