mradermacher/MiniMax-M2-THRIFT-i1-GGUF
Quantization vs lemuralabs/MiniMax-M2-Pruned-25. mradermacher/MiniMax-M2-THRIFT-i1-GGUF is a GGUF quantization (IQ1_M) of the same weights: 311 tensors match exactly and 250 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/249, Attention 0/248, other 0/62, lm_head 0/1