tybuddy/Qwen3.5-122B-A10B-GGUF-archived

Same weights, converted vs Qwen/Qwen3.5-122B-A10B. Same weights stored in another dtype (BF16/F32 → BF16/F32), plus 180 new tensors.

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

On the Hub · Downloads on Model Pulse