mlx-community/deepcogito-cogito-v1-preview-llama-3B-4bit

Quantization vs deepcogito/cogito-v1-preview-llama-3B. mlx-community/deepcogito-cogito-v1-preview-llama-3B-4bit is a quantized version of the other (U32/F16).

On the Hub · Downloads on Model Pulse