Inkling vs. DecentAI

Inkling is an open-weights multimodal AI model from Thinking Machines built to support customization, agentic workflows, coding, reasoning, vision, audio, and enterprise AI use cases. The model is a Mixture-of-Experts transformer with 975 billion total parameters, 41 billion active parameters, 256 routed experts per MoE layer, and six routed experts active per token. It supports context windows up to 1 million tokens and was pretrained on 45 trillion tokens across text, images, audio, and video. Inkling is designed as a broad foundation model rather than a narrowly optimized benchmark model, giving it balanced capabilities across reasoning, coding, factuality, instruction following, vision, audio, tool use, and safety. Its controllable thinking effort lets developers adjust how much computation and generated reasoning the model uses, helping teams balance quality, latency, and cost for different production needs. The model can run agentic coding tasks, use tools, create web apps, generate polished multi-page artifacts, reason over long contexts, and work through iterative refinement loops. For multimodal tasks, Inkling can process images, answer questions about visual content, transcribe and reason over audio, follow spoken instructions, and combine visual reasoning with code-based tools such as Python. Thinking Machines trained Inkling for calibration, instruction following, factual reliability, refusal behavior, and safety across multiple modalities, including evaluations for dangerous capabilities and human-AI threat vectors. Inkling is available on Tinker for fine-tuning, with 64K and 256K context options, an Inkling Playground for testing, cookbook recipes, and support for multimodal post-training workflows. Its full weights are available on Hugging Face, and deployment support is available through APIs and infrastructure partners such as TogetherAI, Fireworks, Modal, Databricks, Baseten, SGLang, vLLM, llama.cpp, and transformers.

DecentAI provides users with a range of features, including access to numerous AI models that can create text, images, audio, and visual content directly from mobile devices. Users have the ability to customize their experience with Model Mixes and flexible model routing, allowing them to combine different models or choose their preferred options. If a model is slow or unavailable, DecentAI will automatically transition to another model, ensuring a consistently smooth and efficient user experience. Emphasizing user privacy, all chats are stored locally on the device rather than on external servers. Additionally, the platform enables AI models to retrieve the most current information through anonymized web searches. In the near future, users will have the opportunity to run models locally on their devices and connect with their own private models, further enhancing customization and control over their AI interactions. This commitment to user empowerment and privacy sets DecentAI apart in the rapidly evolving landscape of artificial intelligence.