
- 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.
