Hi,
I have used Ollama to pull HF GGUF model for local usage according to this post: Use Ollama with any GGUF Model on Hugging Face Hub
The model I have pulled is bartowski/mistralai_Mistral-Small-3.1-24B-Instruct-2503-GGUF · Hugging Face
But I am not sure what is the context length for the pulled model. Is it also as the default as the models from ollama, which is 2048? Or is it the max context length of the model (131072 for this model)
Thanks!
1 Like
It seems that the default is 2048.
# FAQ
## How can I upgrade Ollama?
Ollama on macOS and Windows will automatically download updates. Click on the taskbar or menubar item and then click "Restart to update" to apply the update. Updates can also be installed by downloading the latest version [manually](https://ollama.com/download/).
On Linux, re-run the install script:
```shell
curl -fsSL https://ollama.com/install.sh | sh
```
## How can I view the logs?
Review the [Troubleshooting](./troubleshooting.md) docs for more about using logs.
## Is my GPU compatible with Ollama?
Please refer to the [GPU docs](./gpu.md).
show original
By default, Ollama uses a context window size of 2048 tokens.
Hi @John6666 ,
Thanks for the info! Does it mean the context length for all models pulled by Ollama is always 2048 even if the model is from HF?
If that is the case, looks like I have to change the num_ctx manually after pulling the model
1 Like