Illustration, AI-generated from the story text. Tap a panel to read the story through it.

Thinking Machines uploaded the weights for Inkling 2 Small to Hugging Face on Thursday, a week after launching the model on its Tinker service and promising them for "next week." It has 594 billion in total, 17 billion active per , and takes images.

It ships as and checkpoints; running it takes at least 500GB of memory in the first format and 800GB in the second. Together and DeepInfra already serve it at $1 per million output tokens.

The says outside red-teamers tested it for chemical, biological and cyber risk and found no meaningful uplift beyond existing open models.

There was no launch post. It is now one of the largest American models under a fully permissive license, and it shipped on the date promised.
Thinking Machines puts Inkling 2 Small's weights on Hugging Face under Apache 2.0
Thinking Machines uploaded the weights for Inkling 2 Small to Hugging Face on Thursday, a week after launching the model on its Tinker service and promising them for "next week." It has 594 billion parameters in total, 17 billion active per token, and takes images. It ships as NVFP4 and MXFP8 checkpoints; running it takes at least 500GB of GPU memory in the first format and 800GB in the second. Together and DeepInfra already serve it at $1 per million output tokens.
The model card says outside red-teamers tested it for chemical, biological and cyber risk and found no meaningful uplift beyond existing open models. There was no launch post. It is now one of the largest American models under a fully permissive license, and it shipped on the date promised. SourcesAA
Sources
- AHugging Face: thinkingmachines/Inkling-2-Smallhuggingface.co
- AThinking Machines: Inkling 2 Smallthinkingmachines.ai
This story ran in the Morning Brief of November 13th 2026.