Inkling Details: An Open-Weight General Multimodal Model
clarejtbirch · x · 2026-07-16
Shared details regarding Thinkymachines' new model, Inkling:
- It is a fully open-weight general-purpose model.
- It natively supports text, image, and audio, emphasizing controllable reasoning, customizability, and suitability for agent scenarios.
- A landing page and a Hugging Face link are already available for further trial and exploration.
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
- 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
- Possible open-source MiniMax H3 Max weights appear on Hugging Face, real-time on 8x B200 — BassNet · 2026-09-03