Skip to content

Hugging Face and Thinking Machines Lab Release Inkling 2 Mini

Hugging Face BlogFrom the source·· 1 day agoPicksWelcome Inkling 2 Mini, Cutting-edge Performance for your Local Setup
Original
Image: Hugging Face Blog
Who
Thinking Machines
What
released Inkling 2 Mini, a 24-layer looped transformer
Quote
We are very glad to partner with Thinking Machines Lab to ship Inkling 2 Mini, a performant mid-sized model for local setups.

What happened

Hugging Face and Thinking Machines Lab released Inkling 2 Mini, a multimodal mixture-of-experts model with about 26B total parameters and 3B active per token, designed for local AI setups. It accepts text and images, supports a 1M-token context, and is available with support for Transformers, llama.cpp, MLX, and SGLang. A research variant allows one or two loop passes instead of three for faster inference, though generations may be slightly lower quality; the authors say they have not evaluated it in depth.

Why it matters

Inkling 2 Mini brings a 1M-token context and image input to a model designed for local setups, while its variable-loop research variant trades fewer passes for faster inference and potentially lower output quality.

Reported by 4 sources

    Read next

    See the full storyThinking Machines Releases Inkling 2 Mini
    This story is in 11/21 AI Daily · Lead storyRead the whole issue