Card: definition line (Core AI, 2026-09)
Browse files
README.md
CHANGED
|
@@ -1,3 +1,5 @@
|
|
|
|
|
|
|
|
| 1 |
# MinerU2.5-Pro (1.2B) — Core AI whole-page document parsing
|
| 2 |
|
| 3 |
**On-device whole-page document structuring on Core AI.** A port of
|
|
|
|
| 1 |
+
Core AI is Apple's on-device ML runtime in iOS 27 / macOS 27 and the successor to Core ML: PyTorch models are exported with Apple's `coreai-torch` (LLMs: `coreai.llm.export`) into `.aimodel` bundles that run on the GPU or the Neural Engine, e.g. Qwen3-8B 4-bit decodes at 94 tok/s on an M4 Max GPU, MLX 90 under the same protocol ([apple-silicon-llm-bench](https://github.com/john-rocky/apple-silicon-llm-bench), macOS 27 beta, 2026-06).
|
| 2 |
+
|
| 3 |
# MinerU2.5-Pro (1.2B) — Core AI whole-page document parsing
|
| 4 |
|
| 5 |
**On-device whole-page document structuring on Core AI.** A port of
|