mlx-community/sarashina2.2-3b-instruct-v0.1-4bit

Quantization vs sbintuitions/sarashina2.2-3b-instruct-v0.1. mlx-community/sarashina2.2-3b-instruct-v0.1-4bit is a quantized version of the other (U32/F16).

On the Hub · Downloads on Model Pulse