Thinking Machines Launches Inkling-Small Multimodal Model
baseten · x · 2026-07-31
Thinking Machines Lab has released the new Inkling-Small model, now available on the Baseten platform.
With 276B total parameters and 12B active parameters, it retains the powerful multimodal capabilities and 1M-token context window of the original Inkling. It natively supports text, image, and audio inputs. Designed for efficiency, the smaller footprint allows for faster inference and reduced deployment costs, making it ideal for building complex agentic workflows and RAG applications.
Related event: Thinking Machines Releases Inkling-Small Open-Source Model(23 posts)→
More from Multimodal
- Google Earth Integrates Nano Banana for AI Image Generation — anselm · 2026-07-31
- RTX 4060 Ti Test: Why Does LTX 2.3 Underperform WAN 2.2 in Local Video Generation? — Daniel_Edw · 2026-07-31
- Creator showcases short film generated with Runway Seedance 2.0 — Lucidjordan79 · 2026-07-31
- Can One LoRA Hold Multiple Concepts? Devs Discuss Multi-Style Training Techniques — Lounlysoul007 · 2026-07-31
- Fish Audio Raises $52M Seed, Launches S2.1 Pro Voice Model — thisdudelikesAI · 2026-07-31
- KalpaLabs Launches Conversational Speech Model in Public Beta — ycombinator · 2026-07-31