Downloads · 30 days
231
0% of all-time downloads
kronos-mlx-base
gxcsoccer/kronos-mlx-base
kronos-mlx-base is a time series forecasting model from gxcsoccer. Use it for the time series forecasting task on the model card, and read the license before you ship it in a product. It is set up for kronos-mlx. The card lists the license as mit.
Apple MLX port of NeoQuasar/Kronos-base — the 102M-parameter Kronos variant. dmodel=832, nlayers=12, maxcontext=512. Pair with gxcsoccer/kronos-mlx-tokenizer-base.
All-time downloads
72K
Public
Parameters
102M
409 MB on disk
Likes
8
Public
Repo makeup
Click a slice to open those files.
.safetensors409 MB · 100%
At a glance
- Task
- Time Series Forecasting
- Library
- kronos-mlx
- License
- mit
- Access
- Public
- Created
- Apr 12, 2026
- Updated
- Apr 12, 2026
- SHA
- 52f80e91
Base models
Model card
From the Hugging Face model README
Kronos-base (MLX)
Apple MLX port of NeoQuasar/Kronos-base — the 102M-parameter Kronos variant. d_model=832, n_layers=12, max_context=512. Pair with gxcsoccer/kronos-mlx-tokenizer-base.
Usage
from kronos_mlx import Kronos, KronosTokenizer, KronosPredictor
tokenizer = KronosTokenizer.from_pretrained("gxcsoccer/kronos-mlx-tokenizer-base")
model = Kronos.from_pretrained("gxcsoccer/kronos-mlx-base")
predictor = KronosPredictor(model, tokenizer, max_context=512)
For 8-bit Linear weight quantization (390 MB → ~115 MB, -71 %):
model = Kronos.from_pretrained("gxcsoccer/kronos-mlx-base", bits=8)
8-bit on Kronos-base is much higher fidelity than on Kronos-small thanks to the larger model's redundancy — recommended for memory-constrained Apple Silicon.
Original
- Upstream: shiyu-coder/Kronos (AAAI 2026)
- PyTorch weights: NeoQuasar/Kronos-base
- MLX port: github.com/gxcsoccer/kronos-mlx
- Task
- Time Series Forecasting
- Library
- kronos-mlx
- License
- mit
- Created
- Apr 12, 2026
- Updated
- Apr 12, 2026