mlboydaisuke commited on
Commit
39c19b5
·
verified ·
1 Parent(s): 991b72a

Card: definition line (Core AI, 2026-09)

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -17,6 +17,8 @@ language:
17
  base_model_relation: quantized
18
  ---
19
 
 
 
20
  # Holo2-4B — Core AI (on-device, iPhone) · GUI-grounding VLM
21
 
22
  [Hcompany/Holo2-4B](https://huggingface.co/Hcompany/Holo2-4B) converted to Apple **Core AI**
 
17
  base_model_relation: quantized
18
  ---
19
 
20
+ 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).
21
+
22
  # Holo2-4B — Core AI (on-device, iPhone) · GUI-grounding VLM
23
 
24
  [Hcompany/Holo2-4B](https://huggingface.co/Hcompany/Holo2-4B) converted to Apple **Core AI**