nivvis/Qwen3.5-35B-A3B-EQ-v5-GGUF

Same weights, converted vs nivvis/Qwen3.5-35B-A3B-EQ-v5. Same weights stored in another dtype (BF16 → F16/F32), plus 150 new tensors.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/101, MLP 0/160, Attention 0/40

On the Hub · Downloads on Model Pulse