Feedback

Chat Icon

Local AI Engineering with Ollama

Run, understand, customize, fine-tune, and build agentic apps on your own hardware

Picking and Pulling Models
27%

Understanding How Models Are Stored

After pulling, you can verify the manifest of the model:

# Install jq if needed
# apt install jq

# The path to the models library
MODELS_LIBRARY=${HOME}/.ollama/models/manifests/registry.ollama.ai/library
# Depending on your installation, 
# you might need to adjust the path:
# MODELS_LIBRARY=/usr/share/ollama/.ollama/models/manifests/registry.ollama.ai/library

# Print the manifest
cat $MODELS_LIBRARY/granite3.3/2b | \
    jq

This should show a JSON object that looks like this:

{
  "schemaVersion": 2,
  "mediaType": "application/vnd.docker.distribution.manifest.v2+json",
  "config": {
    "mediaType": "application/vnd.docker.container.image.v1+json",
    "digest": "sha256:f9ed2..",
    "size": 417
  },
  "layers": [
    {
      "mediaType": "application/vnd.ollama.image.model",
      "digest": "sha256:ac71e..",
      "size": 1545303328,
      "from": "/Users/ollama/.ollama/models/blobs/sha256-ac71e.."
    },
    {
      "mediaType": "application/vnd.ollama.image.template",
      "digest": "sha256:3da071..",
      "size": 6560

Local AI Engineering with Ollama

Run, understand, customize, fine-tune, and build agentic apps on your own hardware

Enroll now to unlock all content and receive all future updates for free.