[AINews] Thinky's Inkling: 975B-A41B multimodal, new best American Apache 2.0 open model (with Inkling-Small, 276B-A12B) Thinky's first full LLM release is a banger and bonus: it's open weights! Thinky only seems to come up for air once every few months; most recently with Interaction models - but each time they do they impress, showing both taste and depth. Today they introduced Inkling — not a SOTA model, but a very solid new family for a baseline American open model: - Our model, called Inkling, is a Mixture-of-Experts transformer with 975B total parameters, 41B active. - It supports a con