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
NewsUsing AlphaGo to Stop AI Hallucinations
A former DeepMind researcher wants to use AlphaGo's search methods to fix wrong answers in AI models.
NewsNew AI Tool Fixes Mistakes in Financial Research
Researchers developed a new framework to stop AI from learning from its own bad data in financial trading models.
NewsPerplexity adds local AI to Mac apps
The new update lets your Mac handle some AI tasks directly on your computer.