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