How do you fix "Ollama: Error: model 'X' not found"?

**Pull then run:** ```bash ollama pull llama3.1:8b ollama run llama3.1:8b ``` **Or use `ollama run` directly which auto-pulls if missing in newer versions:** ```bash ollama run llama3.1:8b ``` **Check available models in the library:** ```bash ollama list ``` **Browse the official Ollama library** at [ollama.com/library](https://ollama.com/library) for the exact tag. Common gotcha: the default tag (no `:tag` suffix) varies by model — `llama3.1` defaults to `8b` but `qwen2.5` defaults to `7b`.

RunLocalAI

Configuration

Verified by owner

Ollama: Error: model 'X' not found

Q: What causes "Ollama: Error: model 'X' not found"?

You ran `ollama run ` for a model that hasn't been pulled to your local Ollama library yet. Ollama doesn't auto-pull; `run` only works on already-downloaded models. A second cause: the model name is slightly off. Ollama is case-insensitive but tag-strict — `llama3.1` is different from `llama3.1:8b`.

Error: model 'X' not found, try pulling it first

By Fredoline Eruo · Last verified May 6, 2026

Cause

You ran ollama run <name> for a model that hasn't been pulled to your local Ollama library yet. Ollama doesn't auto-pull; run only works on already-downloaded models.

A second cause: the model name is slightly off. Ollama is case-insensitive but tag-strict — llama3.1 is different from llama3.1:8b.

Solution

Pull then run:

ollama pull llama3.1:8b
ollama run llama3.1:8b

Or use ollama run directly which auto-pulls if missing in newer versions:

ollama run llama3.1:8b

Check available models in the library:

ollama list

Browse the official Ollama library at ollama.com/library for the exact tag. Common gotcha: the default tag (no :tag suffix) varies by model — llama3.1 defaults to 8b but qwen2.5 defaults to 7b.

Related errors

Did this fix it?

If your case was different, email hello@runlocalai.co with what you saw and we'll update the page. If it worked but took different commands on your platform, we want to know that too.