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