Appreciate the great intro! Thank you!
On the MLX examples, I got an error based on the model not being found. It looks like the mlx-community has a slightly different naming convention than the one used in the example.
e.g.
"mlx-community/gemma-4-26b-a4b-bf16" instead of "mlx-community/gemma-4-26B-A4B-it"
The following command worked for me:
▶ mlx_vlm.generate \
--model "mlx-community/gemma-4-26b-a4b-it-4bit" \
--prompt "What is the capital of France?" \
--kv-bits 3.5 \
--kv-quant-scheme turboquant