MLX
English
nima_joint_schema
tool-routing
decision-model
frozen-backbone
joint-schema
custom-code
research
Instructions to use neimand/nima with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use neimand/nima with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download neimand/nima --local-dir nima
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download NOTICE from neimand/nima: direct link, hf CLI and curl.
- Browser
- Download file 368 Bytes
-
https://huggingface.co/neimand/nima/resolve/main/NOTICE
- Command line
-
hf download hf://neimand/nima/NOTICE
-
curl -L -o NOTICE https://huggingface.co/neimand/nima/resolve/main/NOTICE
368 Bytes
| Nima — Joint-Schema V2 decision head | |
| Copyright 2026 Anand Mohanan | |
| This release includes trained head weights and custom MLX inference code from the | |
| mlx-agent-tool-finetuning research project. The frozen Qwen backbone is not included. | |
| Qwen3 is developed by the Qwen team; its MLX conversion is distributed by mlx-community. | |
| No affiliation or endorsement is implied. | |