Downloads · 30 days
8
15% of all-time downloads
neuradex/Qwen3-Embedding-0.6B-CoreML-ANE
Qwen3-Embedding-0.6B-CoreML-ANE is a machine learning model from neuradex. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
CoreML model optimized for Apple Neural Engine. Fixed-shape profiles for maximum ANE throughput. Converted using tooktang/qwen3-ane-embed converter.
Downloads · 30 days
8
15% of all-time downloads
All-time downloads
52
Public
Repo size
2.4 GB
Likes
1
Public
Click a slice to open those files.
.bin4.8 GB · 100%
From the Hugging Face model README
CoreML model optimized for Apple Neural Engine. Fixed-shape profiles for maximum ANE throughput. Converted using tooktang/qwen3-ane-embed converter.
| Profile | Speed | Throughput | CPU/GPU usage |
|---|---|---|---|
| b1_s128 | 25ms | 40 items/sec | zero |
| b1_s512 | 140ms | 7 items/sec | zero |
Runs entirely on Apple Neural Engine — no CPU or GPU load.
| Profile | Batch | Seq len | Use case |
|---|---|---|---|
| b1_s128 | 1 | 128 | Tags, short text |
| b1_s512 | 1 | 512 | Documents, episodes |
compiled/b1_s128.mlmodelc — Pre-compiled, load directly with MLModelcompiled/b1_s512.mlmodelc — Pre-compiledpackages/b1_s128.mlpackage — Source package (for re-compilation)packages/b1_s512.mlpackage — Source packagetokenizer/ — Qwen3 tokenizer filesinput_ids (int32), attention_mask (int32) — left-padded to profile seq_lenembedding (float32, 1024-dim, L2-normalized)Left-pad input tokens to the profile seq_len. Pick the smallest profile that fits your input. The model handles last-token pooling and L2 normalization internally.
ANE-optimized conversion based on tooktang/Qwen3-Embedding-0.6B-CoreML.