masahiroid/chronos-bolt-small-mlx

chronos-bolt-small — MLX

Time series forecasting: 9 quantiles (0.1–0.9), 64 future steps, context up to 2048 observations. No text tokenizer.

Conversion of amazon/chronos-bolt-small at revision 772f3d25d38aec6d914c8949dab4462e2d46f5d8. No fine-tuning or replacement checkpoint. F32 baseline, not a 4-bit quantization. Original authors retain credit and license rights.

Usage and compatibility

Native MLX implementation with the source inference-model tensor names. This custom runtime is not an mlx-lm text-generation model.

Apple Silicon Mac required by the included MLX runtime. Inputs may vary in length (up to the source limit); compiled Apple exports below use fixed shapes.

pip install huggingface_hub mlx numpy

from huggingface_hub import snapshot_download
from pathlib import Path
import sys, numpy as np
path = snapshot_download("masahiroid/chronos-bolt-small-mlx")
sys.path.insert(0, path)
from runtime_mlx import Model
model = Model(path)
forecast = model(context=np.arange(2048, dtype=np.float32)[None, :])
print(np.array(forecast).shape)  # (1, 9, 64)

Numerical validation

Compared against the original PyTorch implementation, 3 deterministic cases. Maximum absolute output difference: 3.8146973e-06; minimum cosine similarity: 1. See validation.json for each case. These are conversion parity checks, not a full task-quality benchmark or latency benchmark.

Text tests cover English emotions, neutral retrieval text, Japanese, empty input and truncation. Chronos tests cover a trend plus sinusoid, a constant series and a series with missing observations. Only applicable tests are used for each model.

Core ML/Core AI text exports use batch 1 and sequence length 128; tokenization must pad/truncate to 128. Chronos Apple exports use batch 1 and context length 2048. MLX/custom GGUF preserve the original maximum context rather than adding training. Short Chronos inputs can be left-padded with NaN for the fixed Apple exports. Forecast horizon remains 64.

Reproducibility

Source revision and output semantics: provenance.json. Conversion scripts are included. Reproduce in a checkout with sources/<original-model-name>/, sources.json and publish/ directories as in the scripts. PyTorch 2.14.1; Transformers 4.57.3; MLX 0.32.4; NumPy 1.26.4 (MLX/Core ML environment); coremltools 9.0; chronos-forecasting 2.3.2; GGUF 0.19.0; Core AI export uses coreai-torch 0.4.3. Core AI validation uses its separate Python 3.14 environment. Version compatibility outside the tested environment is not guaranteed.

License

Weights remain under apache-2.0, with upstream terms in LICENSE. Converter/runtime additions are MIT licensed (CODE_LICENSE). No new task training, safety certification or commercial license is implied.

Other formats

• mlx
• coreml
• coreai
• gguf