bartowski/ReadyArt_gemma-4-31B-it-scotoma-2-GGUF

Same weights, converted (fewer layers) vs ReadyArt/gemma-4-31B-it-scotoma-2. bartowski/ReadyArt_gemma-4-31B-it-scotoma-2-GGUF matches part of ReadyArt/gemma-4-31B-it-scotoma-2 (772 of its 1188 tensors; the rest of ReadyArt/gemma-4-31B-it-scotoma-2 has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → BF16/F32), plus 61 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/361, MLP 0/180, Attention 0/230

On the Hub · Downloads on Model Pulse