meshllm/Qwen3-30B-A3B-Thinking-2507-UD-Q4_K_XL-layers
Quantization (fewer layers) vs unsloth/Qwen3-30B-A3B-Thinking-2507-GGUF. meshllm/Qwen3-30B-A3B-Thinking-2507-UD-Q4_K_XL-layers matches part of unsloth/Qwen3-30B-A3B-Thinking-2507-GGUF (12 of its 579 tensors; the rest of unsloth/Qwen3-30B-A3B-Thinking-2507-GGUF has no counterpart). On the shared part: meshllm/Qwen3-30B-A3B-Thinking-2507-UD-Q4_K_XL-layers is a GGUF quantization (Q4_K/F32) of the same weights: 5 tensors match exactly and 7 within quantization error.
Tensors changed: Norms 0/4, MLP 0/4, Attention 0/4