mradermacher/Qwen1.5-110B-Chat-i1-GGUF
Quantization vs Qwen/Qwen1.5-110B-Chat. mradermacher/Qwen1.5-110B-Chat-i1-GGUF is a GGUF quantization (IQ3_S) of the same weights: 401 tensors match exactly and 562 within quantization error.
Tensors changed: Embeddings 0/1, MLP 0/240, Attention 0/560, Norms 0/161, lm_head 0/1