CrucibleLab/Gemma-4-31B-Loki-Scotoma-V2.0-Swa-4096-GGUF
Quantization (fewer layers) vs CrucibleLab/Gemma-4-31B-Loki-Scotoma-V2.0-Swa-4096. CrucibleLab/Gemma-4-31B-Loki-Scotoma-V2.0-Swa-4096-GGUF matches part of CrucibleLab/Gemma-4-31B-Loki-Scotoma-V2.0-Swa-4096 (772 of its 1188 tensors; the rest of CrucibleLab/Gemma-4-31B-Loki-Scotoma-V2.0-Swa-4096 has no counterpart). On the shared part: CrucibleLab/Gemma-4-31B-Loki-Scotoma-V2.0-Swa-4096-GGUF is a GGUF quantization (Q8_0/BF16) of the same weights: 362 tensors match exactly and 410 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/361, MLP 0/180, Attention 0/230