Magma vs. Inkling

Magma is a state-of-the-art multimodal AI foundation model that represents a major advancement in AI research, allowing for seamless interaction with both digital and physical environments. This Vision-Language-Action (VLA) model excels at understanding visual and textual inputs and can generate actions, such as clicking buttons or manipulating real-world objects. By training on diverse datasets, Magma can generalize to new tasks and environments, unlike traditional models tailored to specific use cases. Researchers have demonstrated that Magma outperforms previous models in tasks like UI navigation and robotic manipulation, while also competing favorably with popular vision-language models trained on much larger datasets. As an adaptable and flexible AI agent, Magma paves the way for more capable, general-purpose assistants that can operate in dynamic real-world scenarios.

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.