DavidAU/Qwen3-55B-A3B-TOTAL-RECALL-Deep-40X-GGUF
Not comparable yet vs Qwen/Qwen3-30B-A3B. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (435 of 18867/975 match), usually an architecture llama.cpp's name map doesn't cover yet.