Warning: This model was not verified with the MNN Chat app; it wouldn't load on my 12 GB RAM phone.
This model DeProgrammer/shisa-v2.1-unphi4-14b-MNN was converted to MNN format from shisa-ai/shisa-v2.1-unphi4-14b using llmexport.py in MNN version 3.4.0 with default settings (4-bit quantization).
Inference can be run via MNN, e.g., MNN Chat on Android.