Instructions to use TiGa-RCE/Qwen3-Embedding-8B-MLX-Q6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use TiGa-RCE/Qwen3-Embedding-8B-MLX-Q6 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Qwen3-Embedding-8B-MLX-Q6 TiGa-RCE/Qwen3-Embedding-8B-MLX-Q6
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
| { | |
| "schema_version": 1, | |
| "published_repository": "TiGa-RCE/Qwen3-Embedding-8B-MLX-Q6", | |
| "family": "Qwen3-Embedding-8B", | |
| "variant": "Q6", | |
| "upstream_repository": "Qwen/Qwen3-Embedding-8B", | |
| "upstream_revision": "1d8ad4ca9b3dd8059ad90a75d4983776a23d44af", | |
| "upstream_revision_evidence": "exact source snapshot retained in local Hugging Face download metadata", | |
| "direct_parent": "TiGa-RCE/Qwen3-Embedding-8B-MLX-BF16", | |
| "direct_parent_weight_hashes": [ | |
| { | |
| "file": "model-00001-of-00004.safetensors", | |
| "sha256": "0a22d58cb671a9049da3505b30b3ba8a200401c4309df397961f61c9c6ab1643", | |
| "bytes": 4900037603 | |
| }, | |
| { | |
| "file": "model-00002-of-00004.safetensors", | |
| "sha256": "18c40e1305906ad2ca3c503efa130f02b20db5940129222cb1728f4a594204ad", | |
| "bytes": 4915960339 | |
| }, | |
| { | |
| "file": "model-00003-of-00004.safetensors", | |
| "sha256": "ce16f97c40ed67ec1b540dcb99259e91a930b431051e50a76350888a2331498c", | |
| "bytes": 4983068481 | |
| }, | |
| { | |
| "file": "model-00004-of-00004.safetensors", | |
| "sha256": "1ac381756541d3601847be3e5ce832a81f308cf8b7afccc1bb65e22c63120cfe", | |
| "bytes": 335570419 | |
| } | |
| ], | |
| "conversion": { | |
| "method": "Q uniform affine quantization", | |
| "nominal_bits": 6, | |
| "group_size": 64, | |
| "importance_matrix": false, | |
| "importance_matrix_samples": null, | |
| "importance_matrix_sequence_length": null, | |
| "stack": { | |
| "omlx": "0.5.3", | |
| "mlx_lm": "0.31.3", | |
| "mlx": "0.32.0" | |
| }, | |
| "lossy_parent": false | |
| }, | |
| "weight_files": [ | |
| { | |
| "file": "model-00001-of-00002.safetensors", | |
| "sha256": "b3dc3953889737b438c42e7f50b1224c3e40c25e6c0f420262e0b92019658579", | |
| "bytes": 5364979113 | |
| }, | |
| { | |
| "file": "model-00002-of-00002.safetensors", | |
| "sha256": "f307e558c08607441046dd35a525d7f237bd2dcb34b83b744b86adb63f29440a", | |
| "bytes": 783917405 | |
| } | |
| ], | |
| "evaluation": { | |
| "pair_count": 24, | |
| "top1": 1.0, | |
| "recall_at_5": 1.0, | |
| "mrr": 1.0, | |
| "mean_aligned_embedding_cosine_vs_bf16": 0.9974064826965332, | |
| "minimum_aligned_embedding_cosine_vs_bf16": 0.9933617115020752, | |
| "score_rmse_vs_bf16": 0.01091226190328598, | |
| "queries_with_rank_change": 0, | |
| "gate_passed": true, | |
| "gate_criteria": { | |
| "top1_delta_min": 0.0, | |
| "recall_at_5_delta_min": 0.0, | |
| "mrr_delta_min": -0.01, | |
| "minimum_aligned_embedding_cosine_min": 0.99, | |
| "queries_with_rank_change_max": 2 | |
| } | |
| }, | |
| "collection": "https://huggingface.co/collections/TiGa-RCE/mlx-embedding-quantization-matrix-q-oq-oqe-at-4-6-8-bit-6a68d11afb238d4fe967d70b" | |
| } | |