mradermacher/DarkIdol-Gemma-4-31B-it-FT-GGUF

Quantization (fewer layers) vs aifeifei798/DarkIdol-Gemma-4-31B-it-FT. mradermacher/DarkIdol-Gemma-4-31B-it-FT-GGUF matches part of aifeifei798/DarkIdol-Gemma-4-31B-it-FT (772 of its 1188 tensors; the rest of aifeifei798/DarkIdol-Gemma-4-31B-it-FT has no counterpart). On the shared part: mradermacher/DarkIdol-Gemma-4-31B-it-FT-GGUF is a GGUF quantization (Q8_0) 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

On the Hub · Downloads on Model Pulse