Thinking Machines Releases Inkling-2-Small Model
Thinking Machines Lab has released Inkling-2-Small, a new multimodal language model available for local deployment. This release marks the introduction of the second generation of Inkling models. The release provides the local LLM community with a new open-weight option featuring advanced capabilities like native image input and large context windows. It expands the choices available for developers looking to run sophisticated models locally. Inkling-2-Small is a sparse Mixture-of-Experts model featuring 594 billion total parameters with 17 billion active parameters. It also supports native image input and up to 1 million tokens of context.
## BACKGROUND
Thinking Machines Lab develops advanced artificial intelligence models, focusing on efficient architectures like sparse Mixture-of-Experts. Local deployment allows users to run these large models on their own hardware for greater privacy and control.