mradermacher/Voxtral-Mini-3B-2507-i1-GGUF
Quantization (fewer layers) vs mistralai/Voxtral-Mini-3B-2507. mradermacher/Voxtral-Mini-3B-2507-i1-GGUF matches part of mistralai/Voxtral-Mini-3B-2507 (273 of its 762 tensors; the rest of mistralai/Voxtral-Mini-3B-2507 has no counterpart). On the shared part: mradermacher/Voxtral-Mini-3B-2507-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 61 tensors match exactly and 212 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/61, MLP 0/90, Attention 0/120, lm_head 0/1