mradermacher/dolphin-2.9.1-qwen-110b-i1-GGUF
Quantization vs dphn/dolphin-2.9.1-qwen-110b. mradermacher/dolphin-2.9.1-qwen-110b-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