Solved: Ollama Can't Pull Latest Model

Solved: Ollama Can't Pull Latest Model

ollama llm

We LOVE Ollama and use it to run both local and cloud-based AI models on our development laptops. That said we've run into a few issues with pulling the latest models over the past few months, so here's how to solve it.

Here are the simple steps to set up a Tailscale on your FreeBSD server:

1. The Problem

We have installed the latest version of Ollama via homebrew, but we still get this error when pulling the latest models:

ollama pull muse-glimmer:30b-mlx

Output:

pulling manifest 
Error: pull model manifest: 412: 
The model you are attempting to pull requires a newer version of Ollama.

Please download the latest version at:

	https://ollama.com/download

2. The Root Cause

You can see the root cause by checking the Ollama version:

ollama -v

Output:

ollama version is 0.32.1
Warning: client version is 0.32.8

The client and the server versions are out of sync, BUT we just updated everything via Homebrew. What gives?

3. The Solution

After much frustration, the solution is actually quite simple: You just need to restart the Ollama server on your development laptop and it'll pickup the new version on startup. Why in the world does this not automatically happen during homebrew install is beyond me.

brew services restart ollama

Then double-check the version to confirm there is no longer a client and server version mismatch:

ollama -v

Output:

ollama version is 0.32.8

4. Conclusion

You can now pull the latest models without any issues.

ollama pull muse-glimmer:30b-mlx

Hope this saves some frustration for you! I know it took me way too long to realize that this was the issue 🤦‍♂️

Cheers 🥂

More Articles