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 For 8 bit Linear weight quantization (390 MB → ~115 MB, 71 % ): 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
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy