Text Generation
MLX
Safetensors
English
nvfp4
4-bit precision
quantized
mixture-of-experts
apple-silicon
custom_code
audio
audio-language-modeling
audio-understanding
text-to-speech
text-to-audio
speech-recognition
speech-translation
long-context
Instructions to use txgsync/Nemotron-Labs-Audex-30B-A3B-NVFP4-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use txgsync/Nemotron-Labs-Audex-30B-A3B-NVFP4-mlx with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # if on a CUDA device, also pip install mlx[cuda] # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("txgsync/Nemotron-Labs-Audex-30B-A3B-NVFP4-mlx") prompt = "Once upon a time in" text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- MLX LM
How to use txgsync/Nemotron-Labs-Audex-30B-A3B-NVFP4-mlx with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "txgsync/Nemotron-Labs-Audex-30B-A3B-NVFP4-mlx" --prompt "Once upon a time"
| { | |
| "add_prefix_space": false, | |
| "backend": "tokenizers", | |
| "bos_token": "<s>", | |
| "clean_up_tokenization_spaces": false, | |
| "eos_token": "</s>", | |
| "is_local": true, | |
| "local_files_only": false, | |
| "model_input_names": [ | |
| "input_ids", | |
| "attention_mask" | |
| ], | |
| "model_max_length": 262144, | |
| "tokenizer_class": "TokenizersBackend", | |
| "tool_parser_type": "qwen3_coder", | |
| "unk_token": "<unk>" | |
| } | |