Inkling Released: Multimodal with Strong Audio Capabilities

thinkymachines · x · 2026-07-16

Inkling natively supports text, audio, and image inputs, with particularly outstanding performance in audio. The author claims it ranks in the first tier among open-weight models on benchmarks like VoiceBench, MMAU, and AudioMC.

Replies add that Inkling exposes cost and latency trade-offs to the user through a "continuous thinking" mechanism: you can achieve the same scores using fewer tokens, allowing for a balance between cost and performance.

Related event: Thinking Machines launches Inkling, its first open-weight multimodal model(169 posts)→

Original post →

More from Models

Models channel →