LLM: MoEs Collection GGUFs, conventional and k-quants – both without imatrix. This should be faster for CPU inference. Right now DeepSee MoEs (Mixture of Experts) • 19 items • Updated 1 day ago
LLM: MoEs Collection GGUFs, conventional and k-quants – both without imatrix. This should be faster for CPU inference. Right now DeepSee MoEs (Mixture of Experts) • 19 items • Updated 1 day ago
LLM: MoEs Collection GGUFs, conventional and k-quants – both without imatrix. This should be faster for CPU inference. Right now DeepSee MoEs (Mixture of Experts) • 19 items • Updated 1 day ago