Speechmatics - API for Voice AI Agents
Mini toolsZamba2 VL 7B
By Zyphra AI
Zamba2-VL-7B is Zyphra’s vision-language model built on the Zamba2 LLM architecture. It supports single-image and multi-image understanding, visual grounding, document and chart reasoning, OCR-style visual text understanding, and general image-text assistant workflows. Zyphra says it is based on Zamba2-7B, uses a Qwen2.5-VL vision encoder, was trained on 100B tokens of vision-text and pure text data, and is designed to keep a small compute and memory footprint for efficient deployment. The model is released under Apache 2.0.
New
Multimodal
Gen 3
Overview
Zamba2-VL-7B is Zyphra’s open 7B-class vision-language model for single-image and multi-image understanding, visual grounding, OCR, charts, documents, and on-device multimodal applications.
About Zyphra AI
Superintelligence that Empowers.
Zyphra is a full stack open source superintelligence company based in San Francisco, California.
Our mission is to build human-aligned AI that helps individuals and organizations reach their fullest potential.
Tools using Zamba2 VL 7B
No tools found for this model yet.
Last updated: June 11, 2026
