WatchDG/Qwen3.8-27B-ABLITERATED-EXL3-3.75bpw

Same weights, converted vs Blackfrost-AI/Qwen3.8-27B-ABLITERATED-BF16. Same weights stored in another dtype (BF16 → I16/BF16), plus 1636 new tensors.

Tensors changed: Norms 0/325, Attention 0/348, MLP 0/112, Embeddings 0/5

On the Hub · Downloads on Model Pulse