Copy the model name.
Use this exact model. Do not guess.
mlx-community/Qwen3.5-9B-MLX-4bit
How To · Model
Download the right model.
This is the easy version. Open the model page, download the model folder, and put it into Cute LM's model directory.
Open Hugging Face.
Go to the tested model page.
Open the model pageDownload the folder.
Download the model files so you end up with one folder named Qwen3.5-9B-MLX-4bit.
Put it in the Cute LM models folder.
Move that folder into your Cute LM model directory. Cute LM is built to look in its local model library.
Cute LM Library/models/Open Cute LM.
When Cute LM starts, it should be able to see the model in that folder.
Next: start Cute LMNeed the runtime?
Cute LM is the next step.
Cute LM is our free, private, offline local runtime. It is preset for SoloRoleplayer//.
Open Cute LMSupport the solo dev.
If this saved you time, please consider supporting WordBlock Labs.
Support on Ko-fi