ibm-research/granite-vision-3.2-2b-GGUF

Same weights, converted (fewer layers) vs ibm-granite/granite-vision-3.2-2b. ibm-research/granite-vision-3.2-2b-GGUF matches part of ibm-granite/granite-vision-3.2-2b (362 of its 815 tensors; the rest of ibm-granite/granite-vision-3.2-2b has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/81, MLP 0/120, Attention 0/160

On the Hub · Downloads on Model Pulse