meshllm/Qwen3-235B-A22B-UD-Q4_K_XL-layers
Quantization (fewer layers) vs unsloth/Qwen3-235B-A22B-GGUF. meshllm/Qwen3-235B-A22B-UD-Q4_K_XL-layers matches part of unsloth/Qwen3-235B-A22B-GGUF (12 of its 1131 tensors; the rest of unsloth/Qwen3-235B-A22B-GGUF has no counterpart). On the shared part: meshllm/Qwen3-235B-A22B-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: MLP 0/4, Norms 0/4, Attention 0/4