mradermacher/Ising-Calibration-1.5-31B-BF16-i1-GGUF
Quantization (fewer layers) vs nvidia/Ising-Calibration-1.5-31B-BF16. mradermacher/Ising-Calibration-1.5-31B-BF16-i1-GGUF matches part of nvidia/Ising-Calibration-1.5-31B-BF16 (772 of its 1188 tensors; the rest of nvidia/Ising-Calibration-1.5-31B-BF16 has no counterpart). On the shared part: mradermacher/Ising-Calibration-1.5-31B-BF16-i1-GGUF is a GGUF quantization (IQ1_M) of the same weights: 361 tensors match exactly and 411 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/361, MLP 0/180, Attention 0/230