jashepp/Agents-A1-35B-A3B-MXFP4_MOE_Hybrid-Imatrix-GGUF
Quantization vs InternScience/Agents-A1. jashepp/Agents-A1-35B-A3B-MXFP4_MOE_Hybrid-Imatrix-GGUF is a GGUF quantization (MXFP4/F16) of the same weights: 143 tensors match exactly and 160 within quantization error.
Tensors changed: Embeddings 0/1, lm_head 0/1, Norms 0/101, MLP 0/160, Attention 0/40