xv0y5ncu/Qwen3.8-27B-GLQ-trellis-3inst-4bpw

Same weights, repacked vs Qwen/Qwen3.8-27B. Same weights in different files (re-saved, re-sharded or new metadata), plus 1600 new tensors.

Tensors changed: Norms 0/325, Attention 0/352, MLP 0/115, Embeddings 0/5, lm_head 0/1, other 0/1

On the Hub · Downloads on Model Pulse