The lms get command allows you to search and download models from online repositories. If no model is specified, it shows staff-picked recommendations.

Models you download via lms get will be stored in your LM Studio model directory.

Parameters

[search term] (optional) : string

The model to download. For specific quantizations, append '@' (e.g., 'llama-3.1-8b@q4_k_m')

--mlx (optional) : flag

Include MLX models in search results

--gguf (optional) : flag

Include GGUF models in search results

--limit (optional) : number

Limit the number of model options shown

--always-show-all-results (optional) : flag

Always show search results, even with exact matches

--always-show-download-options (optional) : flag

Always show quantization options, even with exact matches

--yes (optional) : flag

Skip all confirmations. Uses first match and recommended quantization

Download a model

Download a model by name:

lms get llama-3.1-8b

Specify quantization

Download a specific model quantization:

lms get llama-3.1-8b@q4_k_m

Filter by format

Show only MLX or GGUF models:

lms get --mlx
lms get --gguf

Control search results

Limit the number of results:

lms get --limit 5

Always show all options:

lms get --always-show-all-results
lms get --always-show-download-options

Automated downloads

For scripting, skip all prompts:

lms get llama-3.1-8b --yes

This will automatically select the first matching model and recommended quantization for your hardware.