Research
Excited for our first general model Inkling -- open weights, 975B, natively multimodal (text, image, audio). Available on Tinker, HuggingFac…
Excited for our first general model Inkling -- open weights, 975B, natively multimodal (text, image, audio). Available on Tinker, HuggingFace and partners. It is yours to personalize and use openly. I
Excited for our first general model Inkling -- open weights, 975B, natively multimodal (text, image, audio). Available on Tinker, HuggingFace and partners. It is yours to personalize and use openly. It is yours. Today, we are introducing Inkling. Inkling reasons efficiently across text, image, and audio modalities. We are making the full weights available. https://thinkingmachines.ai/news/introducing-inkling/ Available today for fine-tuning on Tinker. Play with it in the Inkling Playgrou…
Related
- Thinking Machines is impressive. In a couple hours I just fine tuned my own Qwen3.5-397B model this afternoon. Fast usable multimodal is als…
- Congrats to @thinkymachines on the release of TML-Interaction-Small and tying for the top spot on our Audio MC S2S leaderboard! 🥇 Their int…
- Context Unrolling in Omni Models
Source: Soumith Chintala (X) | 2026-07-15