MuXodious/Qwen3.5-4B-MiniFantasy-MTP
Same weights, repacked vs Nubinu/Qwen3.5-4B-MiniFantasy. Same weights in different files (re-saved, re-sharded or new metadata), plus 15 new tensors.
Tensors changed: Embeddings 0/4, Norms 0/203, Attention 0/320, MLP 0/196
2 derivatives checked
- mradermacher/Qwen3.5-4B-MiniFantasy-MTP-GGUF: Same weights, converted
- mradermacher/Qwen3.5-4B-MiniFantasy-MTP-i1-GGUF: Quantization