| jinaai/jina-embeddings-v2-small-enCore ML | 523 MB | 32.7M | – | apache-2.0 | 131万 | 159 | 2025-01-06 |
| jinaai/jina-embeddings-v2-base-enCore ML | 2.2 GB | 137M | – | apache-2.0 | 35.7万 | 739 | 2025-01-06 |
| mlx-community/embeddinggemma-2-bf16MLX基于 google/embeddinggemma-2 | 1.5 GB | 744M | BF16 | apache-2.0 | 6,962 | 11 | 2026-10-06 |
| mlx-community/embeddinggemma-2-8bitMLX基于 google/embeddinggemma-2 | 1.3 GB | 744M | 8-bit | apache-2.0 | 6,514 | 8 | 2026-10-06 |
| mlx-community/Qwen3-Embedding-0.6B-8bitMLX基于 Qwen/Qwen3-Embedding-0.6B | 649 MB | 596M | 8-bit | apache-2.0 | 6,461 | 2 | 2026-07-14 |
| unum-cloud/uform3-image-text-multilingual-baseCore ML | 2 GB | – | – | apache-2.0 | 6,177 | 17 | 2024-12-19 |
| mlx-community/Qwen3-Embedding-4B-4bit-DWQMLX基于 Qwen/Qwen3-Embedding-4B | — | 4B | 4-bit | apache-2.0 | 4,157 | 19 | 2025-06-07 |
| mlx-community/bge-m3-mlx-fp16MLX基于 BAAI/bge-m3 | — | 568M | FP16 | mit | 3,749 | 4 | 2026-03-16 |
| mlx-community/Qwen3-Embedding-8B-4bit-DWQMLX基于 Qwen/Qwen3-Embedding-8B | — | 7.6B | 4-bit | apache-2.0 | 2,491 | 11 | 2025-06-23 |
| mlx-community/bge-m3-mlx-8bitMLX基于 BAAI/bge-m3 | — | 568M | 8-bit | mit | 2,372 | 2 | 2026-03-16 |
| FluidInference/embeddinggemma-2-coremlCore ML基于 google/embeddinggemma-2 | — | – | quantized | apache-2.0 | 2,131 | 32 | 2026-10-09 |
| camstack/camstack-modelsCore ML | — | – | – | other | 1,626 | 0 | 2026-10-22 |
| mlx-community/embeddinggemma-2-mxfp8MLX基于 google/embeddinggemma-2 | — | 744M | 8-bit | apache-2.0 | 1,279 | 5 | 2026-10-06 |
| mlx-community/embeddinggemma-2-4bitMLX基于 google/embeddinggemma-2 | — | 744M | 4-bit | apache-2.0 | 1,166 | 4 | 2026-10-06 |
| mlx-community/Qwen3-VL-Embedding-2B-8bitMLX基于 Qwen/Qwen3-VL-2B-Instruct | — | 2.1B | 8-bit | apache-2.0 | 1,024 | 0 | 2026-03-13 |
| mlx-community/Qwen3-Embedding-8B-mxfp8MLX基于 Qwen/Qwen3-8B-Base | — | 8B* | – | apache-2.0 | 949 | 4 | 2026-02-11 |
| mlx-community/bge-small-en-v1.5-bf16MLX | — | 33.4M | BF16 | mit | 832 | 2 | 2025-04-02 |
| mlx-community/Qwen3-Embedding-4B-mxfp8MLX基于 Qwen/Qwen3-4B-Base | — | 4B | – | apache-2.0 | 801 | 2 | 2026-02-11 |
| mlx-community/CLM-v0.1-8B-MLX-8bitMLX基于 Qwen/Qwen3-8B | — | 8B* | 8-bit | apache-2.0 | 755 | 9 | 2026-09-29 |
| mlx-community/embeddinggemma-2-mxfp4MLX基于 google/embeddinggemma-2 | — | 744M | 4-bit | apache-2.0 | 742 | 3 | 2026-10-06 |
| mlx-community/Qwen3-Embedding-0.6B-mxfp8MLX基于 Qwen/Qwen3-0.6B-Base | — | 596M | – | apache-2.0 | 697 | 3 | 2026-02-11 |
| unum-cloud/uform3-image-text-english-largeCore ML | — | – | – | apache-2.0 | 676 | 5 | 2024-12-19 |
| jinaai/jina-embeddings-v5-text-small-retrieval-mlxMLX基于 jinaai/jina-embeddings-v5-text-small-retrieval | — | 596M | – | cc-by-nc-4.0 | 617 | 4 | 2026-02-27 |
| mlx-community/bge-m3-mlx-4bitMLX基于 BAAI/bge-m3 | — | 568M | 4-bit | mit | 598 | 1 | 2026-03-16 |
| NateRunsA-LIST/alist-food-text-embedderCore ML基于 google/embeddinggemma-2 | — | – | quantized | apache-2.0 | 353 | 0 | 2026-10-08 |
| faxenoff/code-daemon-embed-v1Core ML基于 Alibaba-NLP/gte-modernbert-base | — | 46.8M | INT8 | mit | 205 | 1 | 2026-11-01 |
| wolfram-pro/multilingual-e5-small-coremlCore ML基于 intfloat/multilingual-e5-small | — | – | quantized | mit | 157 | 0 | 2026-09-06 |
| DangerLabs/dm-jepa-1.5Core ML | — | 128M | – | other | 155 | 3 | 2026-10-09 |
| yodayo-ai/jina-embeddings-v2-small-en-stCore ML | — | 32.7M | – | apache-2.0 | 144 | 0 | 2025-06-27 |
| unum-cloud/uform3-image-text-english-smallCore ML | — | – | – | apache-2.0 | 124 | 5 | 2024-12-19 |
| OpenInfinity/embeddinggemma-2-coreml-int8Core ML基于 google/embeddinggemma-2 | — | – | INT8 | apache-2.0 | 107 | 0 | 2026-10-10 |
| FluidInference/granite-embedding-30m-sparse-coremlCore ML基于 ibm-granite/granite-embedding-30m-sparse | — | 30M* | quantized | apache-2.0 | 82 | 1 | 2026-10-09 |
| Arraasz/granite-embedding-small-english-r2-aneCore ML基于 ibm-granite/granite-embedding-small-english-r2 | — | – | FP16 | apache-2.0 | 58 | 1 | 2026-09-25 |
| unum-cloud/uform3-image-text-english-baseCore ML | — | – | – | apache-2.0 | 58 | 3 | 2024-12-19 |
| characteragent/granite-embedding-97m-multilingual-r2-coremlCore ML基于 ibm-granite/granite-embedding-97m-multilingual-r2 | — | 97M* | quantized | apache-2.0 | 54 | 0 | 2026-10-09 |
| Severian/embedCore ML | — | – | – | 未注明 | 50 | 0 | 2024-02-08 |
| haihengh/all-MiniLM-L6-v2-coremlCore ML | — | – | – | apache-2.0 | 47 | 0 | 2026-07-07 |
| H4RUming/embeddinggemma-2-coreml-textCore ML基于 google/embeddinggemma-2 | — | – | quantized | apache-2.0 | 44 | 1 | 2026-10-28 |
| Nemosine/embeddinggemma-2-text-coremlCore ML基于 google/embeddinggemma-2 | — | – | quantized | apache-2.0 | 41 | 0 | 2026-10-15 |
| DangerLabs/dm-jepa-1.5-coremlCore ML | — | – | – | apache-2.0 | 34 | 0 | 2026-10-09 |
| aufklarer/SpeechBrain-ECAPA-VoxCeleb-20M-CoreMLCore ML基于 speechbrain/spkrec-ecapa-voxceleb | — | 20M* | – | apache-2.0 | 32 | 0 | 2026-08-09 |
| apocryphx/embeddinggemma-300m-qat-q4_0-coremlCore ML基于 google/embeddinggemma-300m | — | 300M* | quantized | gemma | 29 | 1 | 2026-09-17 |
| JGKarlin/ohia-bge-m3-coremlCore ML基于 BAAI/bge-m3 | — | – | quantized | mit | 23 | 0 | 2026-08-21 |
| Mannyking/embeddinggemma-2-text-270m-coremlCore ML基于 google/embeddinggemma-2 | — | 270M* | quantized | apache-2.0 | 21 | 1 | 2026-10-23 |
| erjigit17/qwen3-embedding-0.6b-ane-coreml-8bitCore ML基于 neuradex/Qwen3-Embedding-0.6B-CoreML-ANE | — | 0.6B* | 8-bit | apache-2.0 | 20 | 1 | 2026-09-14 |
| usama99athar/multilingual-embedders-onnx-coremlCore ML | — | – | – | mit | 20 | 0 | 2026-08-07 |
| rankun203/granite-embedding-97m-multilingual-r2-coremlCore ML基于 ibm-granite/granite-embedding-97m-multilingual-r2 | — | 97M* | quantized | apache-2.0 | 19 | 0 | 2026-10-06 |
| rankun203/granite-embedding-311m-multilingual-r2-coremlCore ML基于 ibm-granite/granite-embedding-311m-multilingual-r2 | — | 311M* | quantized | apache-2.0 | 18 | 0 | 2026-10-06 |