kyegomez/VLM-Mamba
We introduce VLM-Mamba, the first Vision-Language Model built entirely on State Space Models (SSMs), specifically leveraging the Mamba architecture.
This project offers a new way for AI developers to build Vision-Language Models (VLMs) that understand both images and text. It takes images and text tokens as input and produces integrated vision-language outputs, allowing for tasks like image captioning or visual question answering. AI researchers and machine learning engineers looking to develop more efficient multi-modal AI systems would use this.
Use this if you are an AI developer looking to build vision-language models with significantly reduced memory footprint and faster inference speeds compared to traditional Transformer-based models.
Not ideal if you are a practitioner looking for a ready-to-use, pre-trained VLM for end-user applications without needing to engage in model development.
Stars
14
Forks
1
Language
Python
License
MIT
Category
Last pushed
Jan 05, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/kyegomez/VLM-Mamba"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
NVlabs/MambaVision
[CVPR 2025] Official PyTorch Implementation of MambaVision: A Hybrid Mamba-Transformer Vision Backbone
sign-language-translator/sign-language-translator
Python library & framework to build custom translators for the hearing-impaired and translate...
kyegomez/Jamba
PyTorch Implementation of Jamba: "Jamba: A Hybrid Transformer-Mamba Language Model"
autonomousvision/transfuser
[PAMI'23] TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving;...
kyegomez/MultiModalMamba
A novel implementation of fusing ViT with Mamba into a fast, agile, and high performance...