Back to thinkingmachines
Open WeightsMultimodaltextimageUpdated July 14, 2026

Inkling

Model Overview

Inkling is a 952.4B-parameter Mixture-of-Experts image text to text model developed by thinkingmachines. Built on the InklingForConditionalGeneration architecture. Released on 2026-07-14.


📊 Quick Specs

Specification Table
SpecificationValue
Parameters952.4B
ArchitectureInklingForConditionalGeneration
Taskimage text to text
Modalitytext, image
LicenseAPACHE-2.0
Frameworktransformers
MoEYes
Languages

✨ Key Features

  • 952.4B parameters with sparse MoE architecture for efficient inference
  • Built on InklingForConditionalGeneration architecture (transformers)
  • Primary task: image text to text (text, image modality)
  • Open-weights under APACHE-2.0 license — self-hostable and fine-tunable

📈 Community Adoption

  • 1,547 likes on Hugging Face
  • 27,883 downloads on Hugging Face

🔗 Resources


📜 License & Access

APACHE-2.0 — Open-weights model available for download, fine-tuning, and self-hosted deployment.

Key Features

952.4B parameters with sparse MoE architecture for efficient inference

Feature 01

Built on InklingForConditionalGeneration architecture (transformers)

Feature 02

Primary task: image text to text (text, image modality)

Feature 03

Open-weights under APACHE-2.0 license — self-hostable and fine-tunable

Feature 04

You might also want to compare

Verified Sources

Tags

open-weightstrendinghuggingfacemoetransformersimage-text-to-text

Model Specs

open-weights

Parameters

952.4B

Context Window

unknown

License

APACHE-2.0

Deployment

self-hostable

Resources & Links

Curator Notes

Auto-ingested from HuggingFace Trending on 2026-07-25. Architecture: InklingForConditionalGeneration. Params: 952.4B. License: APACHE-2.0.

Compare Specs

Compare parameters, context windows, modalities, and benchmark scores of this model side-by-side with others.

Compare Model