mradermacher/JGOS-31B-Think-GGUF
Quantization (fewer layers) vs VIDraft/JGOS-31B-Think. mradermacher/JGOS-31B-Think-GGUF matches part of VIDraft/JGOS-31B-Think (772 of its 1188 tensors; the rest of VIDraft/JGOS-31B-Think has no counterpart). On the shared part: mradermacher/JGOS-31B-Think-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