TeichAI/gemma-4-31B-it-Claude-Opus-Distill-GGUF
Same weights, converted (fewer layers) vs TeichAI/gemma-4-31B-it-Claude-Opus-Distill. TeichAI/gemma-4-31B-it-Claude-Opus-Distill-GGUF matches part of TeichAI/gemma-4-31B-it-Claude-Opus-Distill (772 of its 1188 tensors; the rest of TeichAI/gemma-4-31B-it-Claude-Opus-Distill 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
1 derivatives checked
- dylanjkl/JKL-Luau-Gemma-4-31B-it-Claude-Opus-Distill-GGUF: Full fine-tune