This model DeProgrammer/Nanbeige4.1-3B-MNN was converted to MNN format from Nanbeige/Nanbeige4.1-3B using llmexport.py in MNN version 3.4.0 with --quant_bit 8 but otherwise default settings.

Inference can be run via MNN, e.g., MNN Chat on Android.

Downloads last month
9
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for DeProgrammer/Nanbeige4.1-3B-MNN-Q8

Quantized
(29)
this model