mradermacher/glm4.1v-9b-base-sft-i1-GGUF
Quantization vs fremko/glm4.1v-9b-base-sft. mradermacher/glm4.1v-9b-base-sft-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 281 tensors match exactly and 242 within quantization error.
Tensors changed: Norms 0/161, MLP 0/80, Attention 0/280, lm_head 0/1, Embeddings 0/1