Open WeightModel weights are publicly available — can be downloaded and self-hosted
Released September 2026262K context≈ 196,608 words27.36B params
A ternary-weight model that achieves near-lossless 9x compression, fitting a full 27B reasoning model into consumer hardware. Excels at on-device inference for coding, math, vision, and long-context tasks.
Glossary
InferenceThe process of running a trained model to generate predictions or outputs from new inputs.Long-ContextThe ability of a model to process and understand very long sequences of text while maintaining coherence across distant parts of the input.On-DeviceA model designed to run directly on a user's device (phone, laptop, etc.) rather than requiring a remote server.On-Device InferenceRunning a model directly on a user's device (phone, laptop, etc.) rather than sending data to a remote server, which improves privacy and reduces latency.ReasoningThe model's ability to work through multi-step logical problems and provide justified answers rather than just pattern-matching.Reasoning ModelA model trained to show explicit step-by-step reasoning and problem-solving logic before producing final answers, rather than jumping directly to conclusions.