nesymerp1/Gemma-4-Dark-Thoughts-V2-31B-Q4_K_M-Q5_K_S
Quantization (fewer layers) vs Ateron/Gemma-4-Dark-Thoughts-V2-31B. nesymerp1/Gemma-4-Dark-Thoughts-V2-31B-Q4_K_M-Q5_K_S matches part of Ateron/Gemma-4-Dark-Thoughts-V2-31B (772 of its 1188 tensors; the rest of Ateron/Gemma-4-Dark-Thoughts-V2-31B has no counterpart). On the shared part: nesymerp1/Gemma-4-Dark-Thoughts-V2-31B-Q4_K_M-Q5_K_S is a GGUF quantization (Q5_K_S) 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