mradermacher/Roci_Maxx_v2-GGUF

Same weights, converted vs mergekit-community/Roci_Maxx_v2. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/67, MLP 0/99, Attention 0/132

On the Hub · Downloads on Model Pulse