Instructions to use majentik/Qwen3-ASR-0.6B-MLX-6bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use majentik/Qwen3-ASR-0.6B-MLX-6bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Qwen3-ASR-0.6B-MLX-6bit majentik/Qwen3-ASR-0.6B-MLX-6bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
| { | |
| "architectures": [ | |
| "Qwen3ASRForConditionalGeneration" | |
| ], | |
| "audio_config": { | |
| "activation_dropout": 0, | |
| "activation_function": "gelu", | |
| "attention_dropout": 0, | |
| "conv_chunksize": 500, | |
| "d_model": 896, | |
| "downsample_hidden_size": 480, | |
| "dropout": 0, | |
| "encoder_attention_heads": 14, | |
| "encoder_ffn_dim": 3584, | |
| "encoder_layers": 18, | |
| "initializer_range": 0.02, | |
| "max_position_embeddings": 13, | |
| "model_type": "qwen3_asr_encoder", | |
| "n_window": 50, | |
| "n_window_infer": 800, | |
| "num_key_value_heads": 14, | |
| "num_mel_bins": 128, | |
| "output_dim": 1024, | |
| "scale_embedding": false | |
| }, | |
| "audio_token_id": 151676, | |
| "dtype": "bfloat16", | |
| "eos_token_id": [ | |
| 151643, | |
| 151645 | |
| ], | |
| "initializer_range": 0.02, | |
| "model_type": "qwen3_asr", | |
| "pad_token_id": 151645, | |
| "text_config": { | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": null, | |
| "eos_token_id": null, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 1024, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "layer_types": [ | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention" | |
| ], | |
| "max_position_embeddings": 65536, | |
| "max_window_layers": 28, | |
| "model_type": "qwen3", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 28, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": null, | |
| "rms_norm_eps": 1e-06, | |
| "rope_parameters": { | |
| "rope_theta": 1000000, | |
| "rope_type": "default" | |
| }, | |
| "sliding_window": null, | |
| "tie_word_embeddings": true, | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 151936 | |
| }, | |
| "tie_word_embeddings": true, | |
| "timestamp_token_id": 151705, | |
| "token_classification_bias": false, | |
| "transformers_version": "5.13.0.dev0", | |
| "quantization": { | |
| "group_size": 64, | |
| "bits": 6 | |
| }, | |
| "quantization_config": { | |
| "group_size": 64, | |
| "bits": 6 | |
| } | |
| } |