# Thinking Machines releases Inkling 2 Mini, a compact open MoE

> The Apache-2.0 multimodal model uses a mixture-of-experts design aimed at running locally rather than in the cloud.

Published by The Open Weights on Nov 17, 2026. Canonical: https://theopenweights.com/news/inkling-2-mini-i9pi

## Key facts

- Company: Thinkingmachines
- Model: Inkling 2 Mini
- Version: 2-Mini
- Category: Vision-Language
- Modalities: Text / LLM, Vision-Language
- License: Apache 2.0 (Open weights, commercial use allowed)
- Context window: 1.0M tokens
- Architecture: Inkling2LoopForConditionalGeneration
- Precision: INT8
- Weights size: 28.3 GB
- Significance: notable
- Published: 2026-11-17
- Last verified: 2026-11-22
- Hugging Face: https://huggingface.co/thinkingmachines/Inkling-2-Mini
- Canonical URL: https://theopenweights.com/news/inkling-2-mini-i9pi

Thinking Machines has published Inkling 2 Mini, a compact multimodal model released under the permissive Apache-2.0 license. The model handles both text and vision inputs and is distributed on [Hugging Face](https://huggingface.co/thinkingmachines/Inkling-2-Mini), with an accompanying overview on the project's [blog](https://huggingface.co/blog/inkling2mini).

The design leans on a mixture-of-experts (MoE) architecture, which activates only a fraction of the model's parameters for any given input. That approach has become a popular way to deliver stronger capability without paying the full compute cost of a dense model on every token, and it fits the "Mini" framing of a release meant to run close to the user.

## Why it matters

The emphasis here is local deployment. A small, openly licensed vision-language model gives developers an option they can run on their own hardware, without sending images or prompts to a hosted API.

- Apache-2.0 license, permitting commercial use and modification
- Multimodal: accepts text and image inputs
- Mixture-of-experts architecture for efficient inference
- Positioned for local and on-device scenarios

Some specifics remain unstated in the release, including exact parameter counts and the supported context length. Those details will matter for teams weighing Inkling 2 Mini against other compact open models, but the combination of a permissive license and a multimodal, efficiency-minded design makes it a notable addition to the growing field of small open-weight models.

## Get the model

- [Hugging Face](https://huggingface.co/thinkingmachines/Inkling-2-Mini)
- [Announcement](https://huggingface.co/blog/inkling2mini)

## Sources

- [Welcome Inkling 2 Mini, Cutting-edge Performance for your Local Setup](https://huggingface.co/blog/inkling2mini) — Announcement, Nov 20, 2026
- [thinkingmachines/Inkling-2-Mini](https://huggingface.co/thinkingmachines/Inkling-2-Mini) — Hugging Face, Nov 17, 2026

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "Thinking Machines releases Inkling 2 Mini, a compact open MoE", The Open Weights, Nov 17, 2026, https://theopenweights.com/news/inkling-2-mini-i9pi