Card: DeviceMark row (2026-09)
Browse files
README.md
CHANGED
|
@@ -19,6 +19,10 @@ base_model_relation: quantized
|
|
| 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 |
# VoxCPM2 2B — Core AI (on-device, 48 kHz)
|
| 23 |
|
| 24 |
[OpenBMB **VoxCPM2** (2B)](https://huggingface.co/openbmb/VoxCPM2) converted to **Apple Core AI**, running
|
|
|
|
| 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 |
+
<!-- gen-cards:devicemark begin (managed by scripts/gen-cards + tools/devicemark_row.py — edit cards.json, not this block) -->
|
| 23 |
+
This model has no row on [DeviceMark](https://devicemark.github.io/), the on-device LLM leaderboard.
|
| 24 |
+
<!-- gen-cards:devicemark end -->
|
| 25 |
+
|
| 26 |
# VoxCPM2 2B — Core AI (on-device, 48 kHz)
|
| 27 |
|
| 28 |
[OpenBMB **VoxCPM2** (2B)](https://huggingface.co/openbmb/VoxCPM2) converted to **Apple Core AI**, running
|