docker model pull
| Description | Pull a model from Docker Hub or HuggingFace to your local environment |
|---|---|
| Usage | docker model pull MODEL |
Description
Pull a model to your local environment. Downloaded models also appear in the Docker Desktop Dashboard.
Options
| Option | Default | Description |
|---|---|---|
--ignore-runtime-memory-check | Do not block pull if estimated runtime memory for model exceeds system resources. |
Examples
Pulling a model from Docker Hub
docker model pull ai/smollm2
Pulling from HuggingFace
You can pull GGUF models directly from Hugging Face.
Note about quantization: If no tag is specified, the command tries to pull the Q4_K_M version of the model.
If Q4_K_M doesn't exist, the command pulls the first GGUF found in the Files view of the model on HuggingFace.
To specify the quantization, provide it as a tag, for example:
docker model pull hf.co/bartowski/Llama-3.2-1B-Instruct-GGUF:Q4_K_S
docker model pull hf.co/bartowski/Llama-3.2-1B-Instruct-GGUF