mradermacher/Qwen1.5-22B-Chat-Merge-GGUF
Quantization vs DisOOM/Qwen1.5-22B-Chat-Merge. mradermacher/Qwen1.5-22B-Chat-Merge-GGUF is a GGUF quantization (Q8_0) of the same weights: 326 tensors match exactly and 457 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/131, MLP 0/195, Attention 0/455, lm_head 0/1