dicksondickson/Ling-3.0-flash-Sante-oQ4e-mtp-bf16-MLX
This model is a quantization of:
https://huggingface.co/inclusionAI/Ling-3.0-flash-Sante
This model was quantized using oQ (oMLX 0.7.3.dev2) imatrix, mixed-precision quantization with Better Low-Bit oQ.
Important tensors are left at bf16 which is for Apple M3 chips and later.
Run the model using oMLX:
https://github.com/jundot/omlx