跳到正文

Hugging Face and Thinking Machines Lab Release Inkling 2 Mini

Hugging Face Blog当事人·· 1 天前精选Welcome Inkling 2 Mini, Cutting-edge Performance for your Local Setup
打开原文
原文

中文版本尚未就绪 · 显示原文

图片来自 Hugging Face Blog
谁
Thinking Machines
引文
We are very glad to partner with Thinking Machines Lab to ship Inkling 2 Mini, a performant mid-sized model for local setups.

发生了什么

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.

推荐理由

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.

4 家信源报道

    接下来读什么

    查看这件事的完整进展Thinking Machines Releases Inkling 2 Mini
    这条收录于 11月21日 AI 日报 · 头条看这一期日报的全部内容