DevQuasar/LGAI-EXAONE.EXAONE-4.0-32B-GGUF

Same weights, converted vs LGAI-EXAONE/EXAONE-4.0-32B. Same weights stored in another dtype (BF16 → F16/F32), plus 1 new tensors.

Tensors changed: Embeddings 0/1, MLP 0/192, Norms 0/257, Attention 0/256, lm_head 0/1

On the Hub · Downloads on Model Pulse