Instructions to use npario/Qwen3-Embedding-0.6B-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use npario/Qwen3-Embedding-0.6B-8bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download npario/Qwen3-Embedding-0.6B-8bit --local-dir Qwen3-Embedding-0.6B-8bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download config.json from npario/Qwen3-Embedding-0.6B-8bit: direct link, hf CLI and curl.
- Browser
- Download file 857 Bytes
-
https://huggingface.co/npario/Qwen3-Embedding-0.6B-8bit/resolve/main/config.json
- Command line
-
hf download hf://npario/Qwen3-Embedding-0.6B-8bit/config.json
-
curl -L -o config.json https://huggingface.co/npario/Qwen3-Embedding-0.6B-8bit/resolve/main/config.json
857 Bytes
| { | |
| "architectures": [ | |
| "Qwen3ForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151643, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 1024, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "max_position_embeddings": 32768, | |
| "max_window_layers": 28, | |
| "model_type": "qwen3", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 28, | |
| "num_key_value_heads": 8, | |
| "quantization": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000, | |
| "sliding_window": null, | |
| "tie_word_embeddings": true, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.51.3", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 151669 | |
| } |