eaddario/Qwen3-30B-A3B-pruned-GGUF
Same weights, converted vs Qwen/Qwen3-30B-A3B. Same weights stored in another dtype (BF16 → F16/F32), plus 144 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/193, MLP 0/48, Attention 0/192, lm_head 0/1
Same weights, converted vs Qwen/Qwen3-30B-A3B. Same weights stored in another dtype (BF16 → F16/F32), plus 144 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/193, MLP 0/48, Attention 0/192, lm_head 0/1