Open-source framework that allows you to download, set up, and run Large Language Models (LLMs)—like Llama, Mistral, and DeepSeek
Update Jun 18, 2025 tracked by Updatify
does not support generate errors Full Changelog: https://github.com/ollama/ollama/compare/v0.9.1…v0.9.2
Update Jun 9, 2025 tracked by Updatify
The following models now support tool calling:
Tool calling reliability has also been improved for the following models:
To re-download the models, use ollama pull.
A new version of Ollama’s macOS and Windows applications are available to test for early feedback. New improvements to the apps will be introduced over the coming releases:
If you have feedback, please create an issue on GitHub with the app label. These apps will automatically update themselves to future versions of Ollama, so you may have to redownload new preview versions in the future.
Ollama can now be exposed on the network, allowing others to access Ollama on other devices or even over the internet. This is useful for having Ollama running on a powerful Mac, PC or Linux computer while making it accessible to less powerful devices.
Enabling this allows websites to access your local installation of Ollama. This is handy for developing browser-based applications using Ollama’s JavaScript library.
The directory in which models are stored can now be modified! This allows models to be stored on external hard disks or alternative directories than the default.
The macOS app is now a native application and starts much faster while requiring a much smaller installation.
POST predict will now be more informative ollama run would not start Ollama automatically Full Changelog: https://github.com/ollama/ollama/compare/v0.9.0…v0.9.1
Update May 29, 2025 tracked by Updatify
Ollama now has the ability to enable or disable thinking. This gives users the flexibility to choose the model’s thinking behavior for different applications and use cases.
When thinking is enabled, the output will separate the model’s thinking from the model’s output. When thinking is disabled, the model will not think and directly output the content.
Models that support thinking:
When running a model that supports thinking, Ollama will now display the model’s thoughts:
% ollama run deepseek-r1
>>> How many Rs are in strawberry
Thinking...
First, I need to understand what the question is asking. It's asking how many letters 'R' are present in the word "strawberry."
Next, I'll examine each letter in the word individually.
I'll start from the beginning and count every occurrence of the letter 'R.'
After reviewing all the letters, I determine that there are three instances where the letter 'R' appears in the word "strawberry."
...done thinking.
There are three **Rs** in the word **"strawberry"**.
In Ollama’s API, a model’s thinking is now returned as a separate thinking field for easy parsing:
{
"message": {
"role": "assistant",
"thinking": "First, I need to understand what the question is asking. It's asking how many letters 'R' are present in the word "strawberry...",
"content": "There are **3** instances of the letter **R** in the word **"strawberry."**"
}
}
In the API, thinking can be enabled by passing "think": true and disabled by passing "think": false
curl http://localhost:11434/api/chat -d '{
"model": "deepseek-r1",
"messages": [
{
"role": "user",
"content": "Why is the sky blue?"
},
],
"think": true
}'
In Ollama’s CLI, use /set think and /set nothink to enable and disable thinking.
Full Changelog: https://github.com/ollama/ollama/compare/v0.8.0…v0.9.0
Update May 27, 2025 tracked by Updatify
Full Changelog: https://github.com/ollama/ollama/compare/v0.7.1…v0.8.0
Update May 21, 2025 tracked by Updatify
ollama show will now show ... when data is truncated qwen2.5vl llama3.2-vision Full Changelog: https://github.com/ollama/ollama/compare/v0.7.0…v0.7.1
Update May 13, 2025 tracked by Updatify
Ollama now supports multimodal models via Ollama’s new engine, starting with new vision multimodal models:
llama4 on NVIDIA GPUs key not found message ollama run ollama create ollama processes would continue to run after a model was unloaded Full Changelog: https://github.com/ollama/ollama/compare/v0.6.8…v0.7.0
Update May 3, 2025 tracked by Updatify
30b-a3b and 235b-a22b) on NVIDIA and AMD GPUs GGML_ASSERT(tensor->op == GGML_OP_UNARY) failed issue caused by conflicting installations ollama show will now correctly label older vision models such as llava context canceled error Full Changelog: https://github.com/ollama/ollama/compare/v0.6.7…v0.6.8
Update Apr 26, 2025 tracked by Updatify
~ when being provided to ollama run tensor->op == GGML_OP_UNARY errors when running a model due to conflicting inference libraries Stopping... state Full Changelog: https://github.com/ollama/ollama/compare/v0.6.6…v0.6.7