DavidAU/Llama3.2-DeepHermes-3-3B-Preview-Reasoning-MAX-NEO-Imatrix-GGUF

Same weights, converted vs NousResearch/DeepHermes-3-Llama-3-3B-Preview. Same weights stored in another dtype (BF16 → BF16/F32), plus 1 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/112

On the Hub · Downloads on Model Pulse