ollama v0.3 Released With Llama 3.1 Support & Mistral Large 2

For fans of ollama as an open-source means for easily running large language models (LLMs) on your system, ollama v0.3 has been released with support for the newest exciting models.

The ollama v0.3 pre-release that debuted overnight has initial support for Llama 3.1, the newest LLM in the Llama family from Meta/Facebook. Llama 3.1 was introduced earlier this week by Meta as their "most capable" model to date with their 405B version claiming to be "he world’s largest and most capable openly available foundation model."

The ollama 0.3 release is able to handle Llama 3.1 with the 8B, 70B, and 405B parameter sizes. Deploying can be as easy as "ollama run llama3.1" to execute.

The ollama 0.3 release also has support for Mistral Large 2 as Mistral's new 123B model that is more capable across code generation, mathematics, reasoning, and other areas.

Downloads and more details on the ollama 0.3 release via GitHub.