Thinking Machines Lab releases Inkling 2 Small, a 594B-parameter model
Thinking Machines Lab has released Inkling 2 Small, the first model of its second Inkling generation. The sparse MoE model has 594B total and 17B active parameters, accepts text and images, and runs only on Tinker for now. The company plans an Apache 2.0 weights release next week after external safety testing.
