Skip to content
AI Model Radar

North Micro Vision Instruct

CohereLabs/North-Micro-Vision-Instruct
Open Source · chat · open-weights
Open Alert me on changes
Context
8K
Max output
1K
Weights
Open
API $/1M
—
Modalities
text · image
Released
10 Aug 2026
License: apache-2.0 · CohereLabs/North-Micro-Vision-Instruct
Download image Share on X Share on LinkedIn
AI summary
● machine-written

North Micro Vision Instruct: 2.4B multimodal model with native-resolution vision

North Micro Vision Instruct is an open-weights vision-language model from Cohere Labs designed for instruction-following on image and text inputs. The model supports a 128K-token context window in the language backbone, with validated performance up to 8K tokens for multimodal prompts, and was built to handle native-resolution image processing.

What's new
  • Supports text and image inputs with native-resolution vision processing
  • Language backbone supports 128K-token context window; validated multimodal range up to 8K tokens
  • Available under Apache 2.0 license as open-weights model
  • Released August 10, 2026
Best for
Instruction-following on image and text queriesLightweight multimodal inferenceApplications requiring native-resolution image understanding
Sources

Source: https://huggingface.co/CohereLabs/North-Micro-Vision-Instruct