The era of open-source multimodal models has arrived with the introduction of Ollama vision, an open-source multimodal model. Users have reported running the model on various platforms, including Ubuntu 'Server' with an old GTX 1650 and a MacBook. The model allows for local image reasoning and integration with LLaVA and llama_index for building complete multi-modal applications.
Local Multimodal Cookbook with @ollama Vision 🦙📸 Being able to run an image reasoning model on your MacBook is already a superpower. But with our @llama_index integration you can take this to the next-level; build complete multi-modal applications that run completely… https://t.co/hQVBmvYAQx
The new @ollama vision is absolutely amazing! A Vision model running 100% locally on my macbook 🤯 https://t.co/wluy23h7co
Welcome to the era of open-source multimodal models, indeed! This is using: @ollama v0.1.23 (https://t.co/XZ1f5okUVg) Ollama Web UI v1.0.0-alpha.61 (https://t.co/IaG96VAhkZ) LLaVA 1.6 (https://t.co/4uO7Qx3FtI) Running on my Ubuntu "Server" with an old GTX 1650 Nice work… https://t.co/taiFuRReFR
Welcome to the era of open-source multimodal models, indeed! This is using: @ollama v0.1.2 (https://t.co/XZ1f5okUVg) Ollama Web UI v1.0.0-alpha.61 (https://t.co/IaG96VAhkZ) LLaVA 1.6 (https://t.co/4uO7Qx3FtI) Running on my Ubuntu "Server" with an old GTX 1650 Nice work… https://t.co/W28CTCo2AM
Ollama vision is here. Welcome to the era of open-source multimodal models. https://t.co/dGTKedrQNH