mradermacher/Mia-v2-29B-GGUF
Quantization (fewer layers) vs veld-ai/Mia-v2-29B. mradermacher/Mia-v2-29B-GGUF matches part of veld-ai/Mia-v2-29B (772 of its 1188 tensors; the rest of veld-ai/Mia-v2-29B has no counterpart). On the shared part: mradermacher/Mia-v2-29B-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