moot20/Qwen2.5-7B-Instruct-1M-MLX-4bit
Text Generation
•
Updated
•
11
Qwen2.5-1M-MLX
Qwen2.5-Instruct-1M model series - quantized and converted to MLX
-
-
moot20/Qwen2.5-7B-Instruct-1M-MLX-6bits
Text Generation • Updated • 5 -
moot20/Qwen2.5-7B-Instruct-1M-MLX-8bits
Text Generation • Updated • 12 -
moot20/Qwen2.5-14B-Instruct-1M-MLX-4bit
Text Generation • Updated • 549 -
moot20/Qwen2.5-14B-Instruct-1M-MLX-6bits
Text Generation • Updated • 8 -
moot20/Qwen2.5-14B-Instruct-1M-MLX-8bits
Text Generation • Updated • 19