Feature Extraction
MLX
Safetensors
qwen3
embeddings
sentence-similarity
quantization
omlx
q8
8-bit precision
Instructions to use TiGa-RCE/Qwen3-Embedding-8B-MLX-Q8 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-Q8 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Qwen3-Embedding-8B-MLX-Q8 TiGa-RCE/Qwen3-Embedding-8B-MLX-Q8
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
| { | |
| "pair_count": 24, | |
| "top1": 1.0, | |
| "recall_at_5": 1.0, | |
| "mrr": 1.0, | |
| "mean_aligned_embedding_cosine_vs_bf16": 0.9995692372322083, | |
| "minimum_aligned_embedding_cosine_vs_bf16": 0.9993624687194824, | |
| "score_rmse_vs_bf16": 0.0020695074927061796, | |
| "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 | |
| } | |
| } | |