mradermacher/Athenea-4B-VL-Thinking-i1-GGUF
Quantization (fewer layers) vs Aquiles-ai/Athenea-4B-VL-Thinking. mradermacher/Athenea-4B-VL-Thinking-i1-GGUF matches part of Aquiles-ai/Athenea-4B-VL-Thinking (398 of its 713 tensors; the rest of Aquiles-ai/Athenea-4B-VL-Thinking has no counterpart). On the shared part: mradermacher/Athenea-4B-VL-Thinking-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 145 tensors match exactly and 253 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/145, MLP 0/108, Attention 0/144