John1604/Qwen3-Next-80B-A3B-Instruct-gguf

Same weights, converted vs Qwen/Qwen3-Next-80B-A3B-Instruct. Same weights stored in another dtype (BF16 → BF16/F32), plus 180 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/121, MLP 0/240, Attention 0/48, lm_head 0/1

On the Hub · Downloads on Model Pulse