{"id":22509,"date":"2026-07-15T00:00:00","date_gmt":"2026-07-15T00:00:00","guid":{"rendered":"https:\/\/scannn.com\/inkling-our-open-weights-model-thinking-machines-lab\/"},"modified":"2026-07-15T00:00:00","modified_gmt":"2026-07-15T00:00:00","slug":"inkling-our-open-weights-model-thinking-machines-lab","status":"publish","type":"post","link":"https:\/\/scannn.com\/lv\/inkling-our-open-weights-model-thinking-machines-lab\/","title":{"rendered":"Inkling: Our Open-Weights Model - Thinking Machines Lab"},"content":{"rendered":"\n
\n

<\/p>\n

Our mission<\/a> is to build AI that extends human will and judgment. We have developed a platform<\/a> that lets anyone customize models, previewed an AI system<\/a> built for interactive collaboration, and published novel research<\/a>. Today we are advancing our mission by releasing a model we trained from scratch with the full weights available, so that people can make it their own.<\/p>\n

Our model, called Inkling, is a Mixture-of-Experts transformer with 975B total parameters, 41B active. It supports a context window of up to 1M tokens. It was pretrained on 45 trillion tokens of text, images, audio and video. It is the first in a family of models of different sizes: alongside it we are sharing a preview of Inkling-Small, a lighter-weight model with 12B active parameters, trained with a similar recipe, that achieves strong performance with even lower cost and latency.<\/p>\n

Inkling reasons natively over text, images, and audio, and balances cost with performance through efficient and controllable thinking effort. We trained it to be a broad, balanced foundation model: strong across many domains, flexible enough to adapt. Inkling is not the strongest overall model available today, open or closed. Instead, a combination of qualities makes it a good open-weights base for customization: multimodal capabilities, efficient thinking, and availability on Tinker for fine-tuning. Inkling is just the start: our first release in a model family we will continue to build on.<\/p>\n

We want to make customization accessible for more use cases, so Inkling is available for fine-tuning on Tinker today. Picking the right base model to fine-tune is a qualitative judgment that combines measurable benchmarks with the unique feel of a model that comes from playing with it. To enable the latter we\u2019re adding the Inkling Playground in the Tinker console: a developer-facing interface for chatting with Inkling.<\/p>\n

To show what customization means in practice, we asked Inkling to fine-tune itself. Using Tinker, the model wrote its own fine-tuning job, ran it, and evaluated the result:<\/p>\n

\n
\n

\n inkling@tinker: self-finetuning<\/span>\n <\/p>\n

\n
\n
\n
\n
\n <\/p>\n
\n

Build<\/strong> \u00b7 inkling<\/span> \u00b7 tinker-prod<\/p>\n<\/p><\/div>\n<\/p><\/div>\n<\/p><\/div>\n<\/p><\/div>\n

~\/news\/introducing-inkling\/<\/span>
\n 1.33.7<\/span>
\n <\/section>\n