Data◆Article
Inkling is a Mixture-of-Experts transformer with 975B total parameters and 41B active, an Apache-2.0 licensed multimodal model trained on 45 trillion tokens of text, images, audio and video.
Thinking Machines Lab released Inkling, a large Apache-2.0 licensed open-weights MoE multimodal model. ✦ AI generated
Simon Willison · Simon Willison's Weblog · 2026-07-16 · original ↗
Inkling is "a Mixture-of-Experts transformer with 975B total parameters, 41B active" - an Apache-2.0 licensed multimodal model trained on 45 trillion tokens of text, images, audio and video.
Read full article ↗excerpt · fair-use quotation
- ·Mixture-of-Experts transformer, 975B total parameters
- ·Only 41B parameters active per inference
- ·Apache-2.0 licensed, open-weights multimodal model
- ·Trained on 45 trillion tokens: text, images, audio, video
- ·Released by Thinking Machines Lab
- ·Handles text, image, audio, and video inputs
- ·Apache-2.0 license enables open commercial use
Around this claim
This moment responds to
provides context → Inkling is a welcome, competitive addition to the US open-weights ecosystem, being Apache-2.0 licensed and comparable to open-weight models coming out of China, joining NVIDIA Nemotron and Gemma 4 as viable contenders.Simon Willison · Simon Willison's Weblogsupports → Inkling is Thinking Machines Lab's first general model: fully open-weight, 975B total parameters, natively multimodal, and available on Tinker, Hugging Face, and partner platforms.Soumith Chintala · Latent Space