moot20/Qwen2.5-VL-3B-Instruct-MLX-4bits
Image-Text-to-Text
•
Updated
•
11
Qwen2.5-VL
Qwen2.5-VL model series - quantized and converted to MLX
-
-
moot20/Qwen2.5-VL-3B-Instruct-MLX-6bits
Image-Text-to-Text • Updated • 4 -
moot20/Qwen2.5-VL-3B-Instruct-MLX-8bits
Image-Text-to-Text • Updated • 47 • 1 -
moot20/Qwen2.5-VL-7B-Instruct-MLX-4bits
Image-Text-to-Text • Updated • 12 -
moot20/Qwen2.5-VL-7B-Instruct-MLX-6bits
Image-Text-to-Text • Updated • 7 -
moot20/Qwen2.5-VL-7B-Instruct-MLX-8bits
Image-Text-to-Text • Updated • 12