A compact, open-weight text model from the SmolLM3 family, TwIL LM3 handles text-in, text-out tasks with a 65K token context window — enough headroom for longer documents or multi-turn conversations. It ships in both GGUF and safetensors formats, making it practical to run locally or integrate into existing pipelines. Specific capability details beyond its text-focused, small-footprint design are limited.