Type
Type
Local
From
From
LiquidAI
Quantisation
Quantisation
uint8
Precision
Precision
No
Size
Size
700M
Source
Source
This model is the MLX format version of LiquidAI's LFM2-700M, a 700 million parameter language model converted for efficient inference on Apple Silicon using the MLX framework. LFM2 is a Liquid Foundation Model designed for edge deployment and supports multiple languages including English, Arabic, Chinese, French, German, Japanese, Korean, and Spanish. The 8-bit quantized version provides a balance between model performance and computational efficiency for text generation tasks.
This model is the MLX format version of LiquidAI's LFM2-700M, a 700 million parameter language model converted for efficient inference on Apple Silicon using the MLX framework. LFM2 is a Liquid Foundation Model designed for edge deployment and supports multiple languages including English, Arabic, Chinese, French, German, Japanese, Korean, and Spanish. The 8-bit quantized version provides a balance between model performance and computational efficiency for text generation tasks.
Type
Local
From
LiquidAI
Quantisation
uint8
Precision
float16
Size
700M
Source
This model is the MLX format version of LiquidAI's LFM2-700M, a 700 million parameter language model converted for efficient inference on Apple Silicon using the MLX framework. LFM2 is a Liquid Foundation Model designed for edge deployment and supports multiple languages including English, Arabic, Chinese, French, German, Japanese, Korean, and Spanish. The 8-bit quantized version provides a balance between model performance and computational efficiency for text generation tasks.