Card: definition line (Core AI, 2026-09)
Browse files
README.md
CHANGED
|
@@ -8,6 +8,8 @@ tags:
|
|
| 8 |
- on-device
|
| 9 |
---
|
| 10 |
|
|
|
|
|
|
|
| 11 |
# EmbeddingGemma 300m — Core AI export
|
| 12 |
|
| 13 |
[google/embeddinggemma-300m](https://huggingface.co/google/embeddinggemma-300m) as a
|
|
|
|
| 8 |
- on-device
|
| 9 |
---
|
| 10 |
|
| 11 |
+
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).
|
| 12 |
+
|
| 13 |
# EmbeddingGemma 300m — Core AI export
|
| 14 |
|
| 15 |
[google/embeddinggemma-300m](https://huggingface.co/google/embeddinggemma-300m) as a
|