cudabenchmarktest/Qwen3.8-27B-E03-Obliterated-Omni-GGUF
Not comparable yet vs Qwen/Qwen3-Omni-30B-A3B-Instruct. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (0 of 28010/3313 match), usually an architecture llama.cpp's name map doesn't cover yet.