Get the latest tech news

Ollama's new engine for multimodal models


Ollama now supports new multimodal models with its new engine.

We set out to support a new engine that makes multimodal models first-class citizens, and getting Ollama’s partners to contribute more directly the community - the GGML tensor library. Thank you to the teams working to release openly available and powerful vision models - Google DeepMind, Meta Llama, Alibaba Qwen, Mistral, IBM Granite, and the many countless people & labs in the community. Thank you to hardware partners for collaborating and helping to improve inference on a large number of devices - NVIDIA, AMD, Qualcomm, Intel, and Microsoft.

Get the Android app

Or read this on Hacker News

Read more on:

Photo of new engine

new engine

Photo of Ollama

Ollama

Photo of multimodal models

multimodal models

Related news:

News photo

Quick Primer on MCP Using Ollama and LangChain

News photo

Nvidia on NixOS WSL – Ollama up 24/7 on your gaming PC

News photo

Show HN: Job Application Bot by Ollama AI