mradermacher/Qwen2-Audio-7B-i1-GGUF
Quantization (fewer layers) vs Qwen/Qwen2-Audio-7B. mradermacher/Qwen2-Audio-7B-i1-GGUF matches part of Qwen/Qwen2-Audio-7B (387 of its 876 tensors; the rest of Qwen/Qwen2-Audio-7B has no counterpart). On the shared part: mradermacher/Qwen2-Audio-7B-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 161 tensors match exactly and 226 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 0/96, Attention 0/224, lm_head 0/1