Thinking Machines 发布开源多模态模型 Inkling 及小型版
原标题：Welcome Inkling by Thinking Machines
AI 摘要
Thinking Machines Lab 发布了开源多模态模型 Inkling 及其小型版本 Inkling-Small。Inkling 拥有约 1 万亿参数，支持文本、图像和音频输入，具备 1M 上下文窗口和智能体能力，并已在 Hugging Face 上提供，支持 transformers、SGLang、vLLM 和 llama.cpp 等推理引擎。该模型采用混合注意力、短卷积和 MoE 架构，旨在推动多模态推理应用的发展。
正文节选
Inkling now comes in smaller size 🤗 Inkling-Small is out by Thinking Machines Lab. We have updated this post with performance, and deployment configurations for the Inkling-Small and the Inkling-Small-NVFP4 variants. Here’s the collection with all the Inkling models. We made it easier for you to deploy Inkling-Small with one-click on Inference Endpoints (getting up to 160 TPS). We also ship a real-time voice and image demo where you can interact with the model. Inkling is a large (1T params!) op