North Micro Vision Instruct

Cohere · open weight · north-micro-vision-instruct

Compact open-weight vision-language model (2.4B) with native-resolution image support for VQA, captioning, grounding, OCR, charts, and documents. Custom 400M SigLIP 2-based vision encoder + 2B North Micro LLM backbone (Command A+ style). Multilingual and multi-image. LM context 128K; multimodal training validated to 8K. Not a reasoning/tool-calling model. Intended for prototyping and fine-tuning.