Ollama’s Post

View organization page for Ollama, graphic

71,326 followers

IBM's latest Granite 3.1 models and their new embedding models are now available via Ollama. Dense models are designed for tool-based use cases. ollama run granite3.1-dense:2b ollama run granite3.1-dense:8b Mixture of expert models are designed for low latency usage. ollama run granite3-moe:1b ollama run granite3-moe:3b Embedding models are smaller in size in comparison to others with similar performance. English only: ollama pull granite-embedding:30m Multilingual: ollama pull granite-embedding:278m Ollama model pages: Dense: https://lnkd.in/g4GkKk9P MoE: https://lnkd.in/gw84-i-e Embedding: https://lnkd.in/gNCvrB-Q

  • No alternative text description for this image
  • No alternative text description for this image

Get started with Granite 3.1 today ⚡

Kevin Tan H.A.

Digital Transformation Software Engineer & Entrepreneur | Looking for Projects | Multi-lingual

3d

Thinking of using these with Continue.dev. Think I can combine all these and make it work?

Like
Reply

IBM's Granite 3.1 models showcase versatility with dense, MoE, and embedding options!

Like
Reply
Cluff, Jared

Founder @ Genkins Forge AI. Entrepreneur. Former SRE Lead. Generative AI Enthusiast.

4d

I am interested to see how this generation perform. The last struggled against llama 3.2 3b for tool use. I managed to get it to only execute tools about 50% of the time vs 90% for llama3.2

Like
Reply
Venkata Sai Kaparotu

Cloud Data Engineer | AWS & GCP | Big Data Solutions

3d

Tried previous versions and was disappointed a little. Will check these latest models. Hope they made some updates

Md. Golam Mostofa

ML Engineer || Researcher || LLM Engineer || Gen AI || Prompt Engineering || Decentralize AI || Federated Learning || Competitive Programmer || Kaggle Expert || Python Developer || Django Developer

4d

How may the embedding dimension of the emmbeding model?

Manojkumar Parmar

Protecting AI Systems of the World | Founder, CEO & CTO AIShield | Serial Entrepreneur, Technology MetaStrategist, Polymath & Board Member

4d

Ollama and IBM great work! The MOE models are blazingly fast and small. I am going to take them for a spin with agentic use cases where I believe they can unlock the next frontier.

Like
Reply
Hector Goycoolea Ph.D

Associate Director | Data Science Engineering Lead | FSO Americas at EY with expertise in MLOps, NLP, and Cloud Computing.

1d

Let’s try it 🙌

Like
Reply
Dhia Garbaya

Student | Ponts et Chaussées, IP Paris

3d

Take a look at yesterday's Falcon3 release.

  • No alternative text description for this image
Sam Paniagua

Founder | Tech Lead | Full Stack Developer | AI Engineer | Freelance Digital Mercenary | Delivering Scalable, AI-Driven Solutions

4d

Can't wait

Like
Reply
See more comments

To view or add a comment, sign in

Explore topics