Feature Extraction
MLX
Safetensors
qwen3
apple-silicon
quantized
mixed-precision
axquant
axq
development
8bit
8-bit precision
v2
embedding
sentence-similarity
6-bit
Instructions to use AutomatosX/AX-Qwen3-Embedding-0.6B-MLX-AXQ-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use AutomatosX/AX-Qwen3-Embedding-0.6B-MLX-AXQ-8bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir AX-Qwen3-Embedding-0.6B-MLX-AXQ-8bit AutomatosX/AX-Qwen3-Embedding-0.6B-MLX-AXQ-8bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
| { | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151643, | |
| "max_new_tokens": 2048, | |
| "transformers_version": "4.51.3" | |
| } | |