GigaChat
Collection
5 items • Updated • 1
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_MOE
- Downloads last month
- 218
Hardware compatibility
Log In to add your hardware
We're not able to determine the quantization variants.
Model tree for deepsweet/GigaChat3-10B-A1.8-GGUF-MXFP4
Base model
ai-sage/GigaChat3-10B-A1.8B-bf16 Quantized
ai-sage/GigaChat3-10B-A1.8B