Instructions to use verathos-ai/d3-mini-mlx-fp16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use verathos-ai/d3-mini-mlx-fp16 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download verathos-ai/d3-mini-mlx-fp16 --local-dir d3-mini-mlx-fp16
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
d3-mini, MLX package (float16)
d3-mini at revision 0e78bbdbe3cf480ed1461c185c9e0c4fa9258011, packaged for
the Verathos private lane app on Apple silicon: the backbone (float16), the readout over the 255 answer codes
(float32), the tokenizer, and package.json with every file's SHA-256 and size. The package digest (SHA-256 of
package.json) is 9e185af9557d0c588f1b18fdcdbc89abea0754e701ca839b4109a528dddaaa5c.
License: Apache-2.0, as d3-mini and its base model Qwen3.5-4B.
Model size
4B params
Tensor type
F32
·
F16 ·
Hardware compatibility
Log In to add your hardware
Quantized
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support