Open-Source Multimodal Model Inkling Released

BanghuaZ · x · 2026-07-16

Thinkymachines has released Inkling, a multimodal model capable of reasoning across text, image, and audio, with all weights fully open. Starting today, the model is available for fine-tuning on Tinker and can be tested directly in the Inkling Playground.

Additionally, SGLang and Miles are providing Day-0 support for serving and reinforcement learning. They have also validated an end-to-end RL pipeline for Inkling, supporting both full-parameter training and LoRA, which consistently improves reward and evaluation metrics across text and multimodal reasoning tasks.

Related event: Thinking Machines launches Inkling, its first open-weight multimodal model(169 posts)→

Original post →

More from Multimodal

Multimodal channel →