MaziyarPanahi/Qwen3-30B-A3B-Instruct-2507-GGUF

Same weights, converted vs Qwen/Qwen3-30B-A3B-Instruct-2507. 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

On the Hub · Downloads on Model Pulse