ubergarm/Qwen3-Coder-30B-A3B-Instruct-GGUF
Same weights, converted vs Qwen/Qwen3-Coder-30B-A3B-Instruct. Same weights stored in another dtype (BF16 → T158/T153), plus 144 new tensors.
Tensors changed: Norms 0/193, MLP 0/48
Same weights, converted vs Qwen/Qwen3-Coder-30B-A3B-Instruct. Same weights stored in another dtype (BF16 → T158/T153), plus 144 new tensors.
Tensors changed: Norms 0/193, MLP 0/48