2026-07-17Added

Inkling + Nemotron 3 Embed 1B

Thinking Machines Lab's first open-weights foundation model Inkling (975B MoE, 41B active, 1M context, multimodal input with switchable reasoning) and NVIDIA's Nemotron-3-Embed-1B multilingual embedding model (2048 dims, 34 languages) join the catalog via NVIDIA NIM.

InklingFreethinkingmachines/inkling
Nemotron 3 Embed 1BFreenvidia/nemotron-3-embed-1b · Multilingual text embeddings (2048 dimensions, 32k context) for search and RAG.

Looking for the full catalog? Browse all models.