Feature Extraction
MLX
Safetensors
qwen3
embeddings
sentence-similarity
quantization
omlx
oq4e
4-bit precision
Instructions to use TiGa-RCE/Qwen3-Embedding-8B-MLX-oQ4e 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-oQ4e with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Qwen3-Embedding-8B-MLX-oQ4e TiGa-RCE/Qwen3-Embedding-8B-MLX-oQ4e
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
File size: 215 Bytes
9db6783 | 1 2 3 4 5 6 7 8 | {
"prompts": {
"query": "Instruct: Given a web search query, retrieve relevant passages that answer the query\nQuery:",
"document": ""
},
"default_prompt_name": null,
"similarity_fn_name": "cosine"
} |