A Mac-native (Apple Silicon / MLX) mixed-precision build of baidu/Unlimited-OCR (built on DeepSeek-OCR), packaged for the Krill runtime. It parses documents and images to grounded text with no Python and no trust_remote_code — the DeepSeek-MoE language backbone and the DeepEncoder vision tower (SAM-ViT-B + CLIP-L + projector) run natively in Swift + MLX.

It emits grounded OCR, e.g.:

<|det|>title [48, 74, 402, 130]<|/det|>Invoice 2026
<|det|>text  [33, 229, 370, 290]<|/det|>Bill to: Acme Corporation
...

Mixed-precision, single-file model.safetensors (~2.3 GB, from the 6.67 GB bf16 source):

This format is Krill-specific (the native Swift+MLX runtime resolves the per-module quantization); it is not a drop-in transformers checkpoint.

Ships the base view (single 1024 global view → 273 image tokens), which reads full pages including wide layouts. The "gundam" tiling mode (local crops for very dense/large scans) is a follow-up.

All credit to the original authors, baidu/Unlimited-OCR and DeepSeek-OCR. MIT licensed, as upstream.

Quantized and tested by Sourav Singh for Krill, a Mac-native LLM runtime and coding agent in one Swift + MLX binary. More Apple Silicon builds: huggingface.co/srv-sngh. Notes on building with local models and frontier AI: souravailabs.ai · GitHub · LinkedIn · YouTube