GET /api/tags

List all locally available models

Retrieve a list of all models available on the local system. This endpoint returns model metadata including size, modification time, and model details.

Request

Endpoint

GET /api/tags

Headers

HEAD /api/tags

Both GET and HEAD methods are supported.

Request Parameters

No parameters required.

Response

Response Fields

models · array

Array of model objects

Show Model Object

name · string

Display name of the model (shortest unique identifier)

model · string

Full model identifier (same as name)

modified_at · string

Timestamp of last modification (ISO 8601 format)

size · integer

Total size of the model in bytes

digest · string

SHA256 digest of the model manifest

details · object

Model metadata and architecture details

Show Details Object

format · string

Model format (e.g., “gguf”, “safetensors”)

family · string

Model architecture family (e.g., “llama”, “mistral”)

families · array

Array of architecture families the model belongs to

parameter_size · string

Human-readable parameter count (e.g., “7B”, “13B”)

quantization_level · string

Quantization format (e.g., “Q4_0”, “Q5_K_M”, “F16”)

remote_model · string

Name of the upstream model if this is a remote model

remote_host · string

URL of the upstream Ollama host if this is a remote model

Examples

cURL

curl http://localhost:11434/api/tags

Example Response

{
  "models": [
    {
      "name": "llama3.2:latest",
      "model": "llama3.2:latest",
      "modified_at": "2024-02-24T12:34:56.789Z",
      "size": 3826793677,
      "digest": "sha256:8daa9615cce30c259a9555b1cc250d461d1bc69980a274b44d7eda0be78076d8",
      "details": {
        "format": "gguf",
        "family": "llama",
        "families": ["llama"],
        "parameter_size": "3B",
        "quantization_level": "Q4_K_M"
      }
    },
    {
      "name": "mistral:7b-instruct",
      "model": "mistral:7b-instruct",
      "modified_at": "2024-02-20T08:15:30.123Z",
      "size": 4109865159,
      "digest": "sha256:2ae6f6dd7a3dd734790bbbf58b8909a606e0e7e97e94b7604e0aa7ae4490e6d8",
      "details": {
        "format": "gguf",
        "family": "mistral",
        "families": ["mistral"],
        "parameter_size": "7B",
        "quantization_level": "Q4_0"
      }
    }
  ]
}

Filter and Sort (Python Example)

import requests
from datetime import datetime

response = requests.get('http://localhost:11434/api/tags')
models = response.json()['models']

# Sort by size (largest first)
models_by_size = sorted(models, key=lambda m: m['size'], reverse=True)

# Filter by family
llama_models = [m for m in models if m['details']['family'] == 'llama']

# Recently modified (within last 7 days)
from datetime import datetime, timedelta
recent_date = datetime.now() - timedelta(days=7)

recent_models = [
    m for m in models 
    if datetime.fromisoformat(m['modified_at'].replace('Z', '+00:00')) > recent_date
]

print(f"Total models: {len(models)}")
print(f"Llama models: {len(llama_models)}")
print(f"Recently modified: {len(recent_models)}")

Display Model Information (JavaScript Example)

const response = await fetch('http://localhost:11434/api/tags');
const data = await response.json();

data.models.forEach(model => {
  const sizeGB = (model.size / (1024 ** 3)).toFixed(2);
  const date = new Date(model.modified_at);
  
  console.log(`
    Model: ${model.name}
    Family: ${model.details.family}
    Size: ${sizeGB} GB
    Parameters: ${model.details.parameter_size}
    Quantization: ${model.details.quantization_level}
    Modified: ${date.toLocaleDateString()}
  `);
});

Error Responses

error · string

Description of the error

Common Errors

• 500 Internal Server Error: Error reading model directory

Models are sorted by modification time, with the most recently modified models appearing first.

The name and model fields contain the same value - the shortest unique identifier for the model (e.g., llama3.2 instead of registry.ollama.ai/library/llama3.2:latest).