deepsweet/GigaChat3-10B-A1.8-GGUF-MXFP4
042
This model was converted to GGUF MXFP4 format from ai-sage/GigaChat3-10B-A1.8B using llama.cpp version 8190:
llama-quantize GigaChat3-10B-A1.8-f32.gguf GigaChat3-10B-A1.8-GGUF-MXFP4.gguf MXFP4_MOEThis model was converted to GGUF MXFP4 format from ai-sage/GigaChat3-10B-A1.8B using llama.cpp version 8190:
llama-quantize GigaChat3-10B-A1.8-f32.gguf GigaChat3-10B-A1.8-GGUF-MXFP4.gguf MXFP4_MOE