LGAI-EXAONE/EXAONE-4.5-33B-GGUF

Same weights, converted (fewer layers) vs LGAI-EXAONE/EXAONE-4.5-33B. LGAI-EXAONE/EXAONE-4.5-33B-GGUF matches part of LGAI-EXAONE/EXAONE-4.5-33B (707 of its 1064 tensors; the rest of LGAI-EXAONE/EXAONE-4.5-33B has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → BF16/F32), plus 16 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