mradermacher/NoisyRollout-MMK12-6.4K-32B-i1-GGUF
Quantization (fewer layers) vs xyliu6/NoisyRollout-MMK12-6.4K-32B. mradermacher/NoisyRollout-MMK12-6.4K-32B-i1-GGUF matches part of xyliu6/NoisyRollout-MMK12-6.4K-32B (771 of its 1161 tensors; the rest of xyliu6/NoisyRollout-MMK12-6.4K-32B has no counterpart). On the shared part: mradermacher/NoisyRollout-MMK12-6.4K-32B-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 321 tensors match exactly and 450 within quantization error.
Tensors changed: Norms 0/129, Attention 0/448, MLP 0/192, lm_head 0/1, Embeddings 0/1