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.
More from Multimodal
- Grok Imagine lets you combine up to 14 references in a single video generation — XFreeze · 2026-09-03
- Gemini Flash 3.8 image-to-SVG test sparks claim SVG may replace image models in 18 months — Kyrannio · 2026-09-03
- Open-source "Yingzao" skill turns travel photos into magazine-grade cultural posters — 歸藏的AI工具箱 · 2026-09-03
- Higgsfield's new Genjutsu motion-copy tool impresses: better than Kling motion control? — rheylew · 2026-09-03
- Team claims h3 max is the undisputed #1 frontier video model across benchmarks — isidentical · 2026-09-03
- Fable 5.1 makes three.js sites: faster and sharper, but taste still matters — repligate · 2026-09-03