SandLogicTechnologies/granite-docling-258M-GGUF

Quantization (fewer layers) vs ibm-granite/granite-docling-258M. SandLogicTechnologies/granite-docling-258M-GGUF matches part of ibm-granite/granite-docling-258M (272 of its 470 tensors; the rest of ibm-granite/granite-docling-258M has no counterpart). On the shared part: SandLogicTechnologies/granite-docling-258M-GGUF is a GGUF quantization (Q6_K) of the same weights: 61 tensors match exactly and 211 within quantization error.

Tensors changed: Embeddings 0/1, Norms 0/61, MLP 0/90, Attention 0/120

On the Hub · Downloads on Model Pulse