moxin-org

/

Nemotron-3-Nano-30B-A3B-GGUF

like 3

Follow

Moxin Organization 55

https://github.com/ggml-org/llama.cpp/blob/master/gguf-py/gguf/constants.py#L3371

Due to the architecture and tensor shapes, only quantization options with a block size of 32 appear to be compatible at this point.