tnhnyzc/Step-3.5-Flash-MTP-GGUF
Quantization vs stepfun-ai/Step-3.5-Flash. tnhnyzc/Step-3.5-Flash-MTP-GGUF is a GGUF quantization (IQ3_S/IQ4_XS) of the same weights: 227 tensors match exactly and 496 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/185, MLP 0/264, Attention 0/230, other 0/42, lm_head 0/1