Instructions to use ekryski/SmolLM2-360M-Instruct-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use ekryski/SmolLM2-360M-Instruct-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download ekryski/SmolLM2-360M-Instruct-4bit --local-dir SmolLM2-360M-Instruct-4bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
|
Download README.md from ekryski/SmolLM2-360M-Instruct-4bit: direct link, hf CLI and curl.
- Browser
- Download file 957 Bytes
-
https://huggingface.co/ekryski/SmolLM2-360M-Instruct-4bit/resolve/main/README.md
- Command line
-
hf download hf://ekryski/SmolLM2-360M-Instruct-4bit/README.md
-
curl -L -o README.md https://huggingface.co/ekryski/SmolLM2-360M-Instruct-4bit/resolve/main/README.md
957 Bytes
metadata
license: apache-2.0
base_model: HuggingFaceTB/SmolLM2-360M-Instruct
language:
- en
tags:
- mlx
- ffai
- quantized
- 4bit
- affine
SmolLM2-360M-Instruct-4bit
4-bit affine quantization of HuggingFaceTB/SmolLM2-360M-Instruct, produced with FFAI 0.1.0's ffai convert (mlx-affine format, group_size=64).
Conversion
ffai convert HuggingFaceTB/SmolLM2-360M-Instruct --bits 4 \
--upload-repo ekryski/SmolLM2-360M-Instruct-4bit
See also
- FFAI — fast Apple Silicon LLM inference.
Model.load("ekryski/SmolLM2-360M-Instruct-4bit")runs this checkpoint end-to-end. - FFAI quickstart
- FFAI quantization docs