DevQuasar-11/LGAI-EXAONE.EXAONE-Deep-32B-GGUF

Same weights, converted vs LGAI-EXAONE/EXAONE-Deep-32B. Same weights stored in another dtype (BF16 → F16/F32), plus 1 new tensors.

Tensors changed: Attention 0/256, Norms 0/129, MLP 0/192, Embeddings 0/1, lm_head 0/1

On the Hub · Downloads on Model Pulse