Thinking Machines Lab Launches Inkling-Small
Thinking Machines Lab just released Inkling-Small. It has 276 billion total parameters but uses only 12 billion active parameters. This design makes the model much more efficient than the original version.
Even though it is four times smaller, it matches the performance of the full-sized model. It can handle both text and images with high accuracy.
The best part is its hardware requirements. You can now run a full checkpoint on a single NVIDIA B300 GPU. This makes powerful AI more accessible for researchers and developers.
Comments (0)
No comments yet. Be the first!
More AI news
NewsHow to Map Building Footprints Using AI
Learn how to build a custom tool that identifies building outlines from aerial photos.
NewsMeta gives AI a memory coach to stop repeating mistakes
Meta created a second AI agent to help the main AI remember past errors and finish complex tasks correctly.
NewsOpenAI launches Presence for business AI agents
OpenAI is rolling out a new service called Presence to help companies launch AI agents for real work.