Model Library
Browse and deploy state-of-the-art AI models through the DevUp Gateway.
Back to Models
thinkingmachines /
Inkling-Small
203 DZD in 504 DZD out 40.6 DZD cached/ 1M tokens
Inkling-Small is a Mixture-of-Experts transformer with 276B total parameters, 12B active, trained on NVIDIA GB300 NVL72 systems. Like Inkling, it features native reasoning over audio and images, variable thinking effort
ArchitectureTransformer
Context Window524K