mradermacher/Qwen2.5-Omni-7B-i1-GGUF
Not comparable yet vs Qwen/Qwen2.5-Omni-7B. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (97 of 2448/339 match), usually an architecture llama.cpp's name map doesn't cover yet.
Not comparable yet vs Qwen/Qwen2.5-Omni-7B. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (97 of 2448/339 match), usually an architecture llama.cpp's name map doesn't cover yet.