mradermacher/SmolDocling-256M-preview-GGUF
Same weights, converted (fewer layers) vs docling-project/SmolDocling-256M-preview. mradermacher/SmolDocling-256M-preview-GGUF matches part of docling-project/SmolDocling-256M-preview (273 of its 471 tensors; the rest of docling-project/SmolDocling-256M-preview has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/61, MLP 0/90, Attention 0/120