
Apologies that I haven't written anything since joining Thinking Machines but I hope this blog post on a topic very near and dear to my heart (reproducible floating point numerics in LLM inference) will make up for it!
✓@thinkymachines Formerly @PyTorch "My learning style is Horace twitter threads" - @typedfemale

Apologies that I haven't written anything since joining Thinking Machines but I hope this blog post on a topic very near and dear to my heart (reproducible floating point numerics in LLM inference) will make up for it!

Inkling 2 Small is our first model trained partly in NVFP4, with a mixed-precision recipe that enables a great tradeoff between speed and accuracy. Check out our new post to see how we did it, and the lessons we learned along the way!

When I first talked to @jackcookjack, he thought that although he was having fun working on nvfp4 pretraining in academia, he was skeptical that it would ever actually work for actual large-scale runs. As it turns out, he was wrong :^) This blog post explains how it can be done

I'll be giving a talk tomorrow at the SGLang Summit at 10am! Oftentimes, I find explanations in ML infra to be unsatisfying. A common failure mode is that they'll explain the *literal* tradeoffs but fail to provide a mental model for how to reason about the choice. This talk won't explain everything about inference (only 15 minutes!), but I'll provide two mental models I've found useful when reasoning about inference, and I hope you find them useful too :)


We just added Inkling 2 Small to MathArena! Strong performance for an open model, especially on BrokenArXiv, where it takes away the top spot among open models.


Ahead of our open weights release, we'd like to encourage folks to try out the model for cool things, whether that's evals, building a cool demo, or posttraining it! If you have some good ideas, comment below or DM your email and we can give you some tinker credits to try it :)



Inkling 2 Small pushes the cost-performance pareto frontier for OSS models on DeepFinance bench On long horizon finance workflows, Inkling 2 Small scores higher than GLM 5.3 for 50% of the cost, and nearly the same score as Qwen 3.8 max for 11% of the cost

Inkling 2 Small can paint 👩🎨!! (Video + Audio made in code) Comparison below between GLM 5.3 Flash, DeepSeek V4.1 Flash and Qwen 3.8 Flash on the same prompts. ⬇️

Inkling 2 Small from @thinkymachines on ARC-AGI (Verified): - ARC-AGI-2: 81.7%, $0.27/task - ARC-AGI-1: 96.5%, $0.08/task It outperforms every open-weight model we've evaluated on both ARC-AGI-1 & ARC-AGI-2. Thinking Machines plans to release its full weights next week.

Inkling 2 is a great model especially for multimodal tasks! just tested it on internal benchmarks for image generation & editing judging, and it's better than kimi and muse. looking forward to fine-tuning Inkling on Tinker.

