Visual TL;DR
Cut CostsDriver
Thinking Machines Lab aims to gain ground against competitors by reducing compute requirements
From the articleThe model allows users to adjust reasoning effort, letting them choose between lower costs or higher performance.
Inkling-Small ModelCore
a 276B parameter model designed to compete with larger systems efficiently
From the article 7 mentionsThinking Machines Lab today announced the Inkling-Small release, an efficient open-weights model designed to compete with larger systems while slashing compute requirements.
Mixture-of-ExpertsContext
From the articleThe model functions as a mixture-of-experts transformer, utilizing 12 billion active parameters out of 276 billion total.
Comparable PerformanceEffect
achieves parity with the larger 975B parameter Inkling model on key benchmarks
From the articleThe model allows users to adjust reasoning effort, letting them choose between lower costs or higher performance.
StartupHub.ai ScoreContext
original Inkling scored 54/100, behind Intapp (70/100) but ahead of 360Learning (45/100)
From the articleStartupHub.ai data assigns the original Inkling a score of 54/100.
Exceeds SWEBench-VerifiedEffect
From the articleTesting shows Inkling-Small exceeding 80 percent on SWEBench-Verified.
Retains CapabilitiesEffect
From the articleIt retains the native audio and image processing capabilities found in the larger version.
Fraction of CostOutcome
delivers comparable performance to its larger predecessor at a significantly reduced cost
From the articleThe model allows users to adjust reasoning effort, letting them choose between lower costs or higher performance.