Putting language-model workloads on a personal device changes the trade-off: prompts and documents can stay local, but the model has far less capacity than a cloud-scale system. This release makes that compromise tangible—a compact Windows-oriented model with a long context window, but explicitly limited world knowledge and complex reasoning.
Aion 1.0 Instruct 2.3B
Runs text generation, summarization, and question answering directly on Windows devices as a 2.3B-parameter instruction-tuned model. It supports eight languages and a 32K context window, trading broad world knowledge and deep reasoning for local execution and privacy.
Introduction
Information
- Websitehuggingface.co
- OrganizationsMicrosoft Windows Applied Sciences Group, Microsoft Windows & Devices
- Published date2026/11/18
Categories
More Items
Handles text, image, and video understanding with sparse attention designed for contexts up to 1 million tokens. It has 770B total parameters with 49B activated per token, targeting long-document analysis, multimodal reasoning, and extended workflows.
Estimates metric depth for every pixel in a photo, video, or live feed, with sharp object boundaries and stable results across frames. Multiple model sizes are available; weights are restricted to non-commercial research and academic development.
Provides quantized GGUF builds of Inkling 2 Mini for local text-and-image inference, with file sizes from about 7.76 to 22.87 GB. Runtime support for its looped transformer architecture may vary.