MuXodious/MiniCPM-V-4.6-Thinking-heretic-MTP-GGUF

Same weights, converted vs MuXodious/MiniCPM-V-4.6-Thinking-heretic-MTP. Same weights stored in another dtype (BF16 → BF16/F32), plus 33 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/61, MLP 0/72, Attention 0/24

On the Hub · Downloads on Model Pulse