Card: DeviceMark row (2026-09)
Browse files
README.md
CHANGED
|
@@ -9,6 +9,10 @@ base_model_relation: quantized
|
|
| 9 |
|
| 10 |
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).
|
| 11 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
# Streaming Sortformer 4-spk v2 — Core AI
|
| 13 |
|
| 14 |
[`nvidia/diar_streaming_sortformer_4spk-v2`](https://huggingface.co/nvidia/diar_streaming_sortformer_4spk-v2)
|
|
|
|
| 9 |
|
| 10 |
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).
|
| 11 |
|
| 12 |
+
<!-- gen-cards:devicemark begin (managed by scripts/gen-cards + tools/devicemark_row.py — edit cards.json, not this block) -->
|
| 13 |
+
This model has no row on [DeviceMark](https://devicemark.github.io/), the on-device LLM leaderboard.
|
| 14 |
+
<!-- gen-cards:devicemark end -->
|
| 15 |
+
|
| 16 |
# Streaming Sortformer 4-spk v2 — Core AI
|
| 17 |
|
| 18 |
[`nvidia/diar_streaming_sortformer_4spk-v2`](https://huggingface.co/nvidia/diar_streaming_sortformer_4spk-v2)
|