mradermacher/LLama-3.1-8b-Ultra-Max-Pro-GGUF

Same weights, converted vs bunnycore/LLama-3.1-8b-Ultra-Max-Pro. Same weights stored in another dtype (F16 → F16/F32), plus 1 new tensors.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/65, MLP 0/96, Attention 0/128

On the Hub · Downloads on Model Pulse