Inkling Released: A Cross-Modal Reasoning Model
thinkymachines · x · 2026-07-16
Thinky Machines has released a new model named Inkling.
- It is capable of efficient reasoning across multiple modalities, including text, images, and audio.
- The team confirmed that full model weights will be open-sourced.
- Users can already fine-tune it on Tinker and try it out directly in the Inkling Playground.
This release marks a new option tailored for multimodal reasoning and open-weight use cases.
More from Multimodal
- Midjourney style code share: --sref 2912175708 — tisch_eins · 2026-09-11
- Astra storyboards plus Minimax H3 per-shot generation boost video success rates — Hailuo_AI · 2026-09-11
- MiniMax H3 MAX nails cooking anime clips: 15-second curry demo with prompts shared — Hailuo_AI · 2026-09-11
- MiniMax Music Production Toolkit 2.5 for ComfyUI adds full mastering chain — Vivid_Promise1700 · 2026-09-11
- New Node Finder for ComfyUI ranks fresh nodes by star velocity and recency — Luke2642 · 2026-09-11
- Using a finisher move on one mosquito with MiniMax H3 MAX — the bug survives — Hailuo_AI · 2026-09-11