lc models <command> [arguments] [flags]

lc models list

# Aliases
lc models ls
lc model list
lc m ls

lc models pull <model-name>

# Aliases
lc models download <model-name>
lc models get <model-name>

# Examples
lc models pull llama3.2:3b
lc models pull mistral:7b
lc models pull all-minilm:l6-v2

lc models remove <model-name>

# Aliases
lc models rm <model-name>
lc models delete <model-name>

# Examples
lc models remove llama3.2:3b
lc models rm mistral:7b

lc models info

lc models list

AI Models (Ollama)























































Language Models:
 llama3.2:3b        2.0GB    Active     2024-01-15
� mistral:7b         4.1GB    Available  2024-01-10
� codellama:7b       3.8GB    Available  2024-01-08

Embedding Models:
 all-minilm:l6-v2   91MB     Active     2024-01-12
� nomic-embed-text   274MB    Available  2024-01-05

Total: 5 models, 7.1GB used
Active: llama3.2:3b (LLM), all-minilm:l6-v2 (Embedding)

lc models pull llama3.2:3b

Downloading llama3.2:3b...























































Pulling model: llama3.2:3b
�������������������������������������� 100% 2.0GB/2.0GB

 Model downloaded successfully!

Model Information:
- Name: llama3.2:3b
- Type: Language Model
- Size: 2.0GB
- Parameters: 3 billion
- Context: 128k tokens

Usage Examples:
# Test the model
curl http://localhost:11434/api/generate -d '{
  "model": "llama3.2:3b",
  "prompt": "Hello! Tell me about yourself.",
  "stream": false
}'

# Use in your application
import requests
response = requests.post('http://localhost:11434/api/generate', 
  json={'model': 'llama3.2:3b', 'prompt': 'Hello!'})

lc models remove mistral:7b

Remove model: mistral:7b (4.1GB)

This will permanently delete the model and free up 4.1GB of disk space.
Are you sure? (y/N): y

 Model 'mistral:7b' removed successfully
 Freed 4.1GB of disk space

lc models info

AI Service Status























































Ollama Service:
 Status: Running
 Version: 0.1.17
 API: http://localhost:11434
 Models Directory: ~/.ollama/models

Model Statistics:
- Total Models: 5
- Language Models: 3
- Embedding Models: 2
- Total Size: 7.1GB
- Available Space: 45GB

Active Models:
- LLM: llama3.2:3b (default)
- Embedding: all-minilm:l6-v2 (default)

Memory Usage:
- Used: 2.4GB
- Available: 13.6GB
- Models in Memory: 1

# Recommended models
lc models pull qwen2.5:3b      # Best overall
lc models pull phi3:3.8b       # Good for reasoning
lc models pull gemma2:2b       # Fastest responses

# Balanced performance
lc models pull llama3.2:7b     # High quality
lc models pull mistral:7b      # Great for code
lc models pull codellama:7b    # Specialized coding

# High performance models
lc models pull mixtral:8x7b    # Mixture of experts
lc models pull qwen2.5:32b     # Advanced reasoning
lc models pull llama3.1:70b    # Best quality

lc models pull llama3.2:3b     # Small, fast
lc models pull llama3.2:7b     # Better quality

lc models pull codellama:7b    # Code-specialized
lc models pull deepseek-coder:6.7b  # Advanced coding

# Language model
lc models pull llama3.2:7b

# Embedding model
lc models pull all-minilm:l6-v2      # Fast
lc models pull nomic-embed-text      # High quality

lc models pull wizardmath:7b   # Math-specialized
lc models pull qwen2.5:7b      # Strong reasoning

services:
  ai:
    models:
      - name: llama3.2:3b
        type: llm
        default: true
      - name: all-minilm:l6-v2
        type: embedding
        default: true

# Update to newer version
lc models pull llama3.2:latest

# Remove old version
lc models remove llama3.2:3b

# Update embedding model
lc models pull all-minilm:latest

# Download multiple models
lc models pull llama3.2:3b mistral:7b codellama:7b

# Remove multiple models
lc models remove old-model:v1 test-model:experimental

# Check memory usage
lc models info

# If memory is low, use smaller models
lc models remove large-model:70b
lc models pull efficient-model:3b

# Check disk usage
lc models list

# Clean up unused models
lc models remove unused-model:7b

# Keep only essential models
lc models remove $(lc models list --inactive)

Error: failed to download model 'llama3.2:3b'

Error: model 'custom-model' not found

Error: insufficient memory to load model

Error: cannot connect to Ollama service

# Generate text
curl http://localhost:11434/api/generate -d '{
  "model": "llama3.2:3b",
  "prompt": "Explain quantum computing",
  "stream": false
}'

# Create embeddings
curl http://localhost:11434/api/embeddings -d '{
  "model": "all-minilm:l6-v2",
  "prompt": "This is a test sentence"
}'

# Python example
import requests

def chat_with_model(prompt, model="llama3.2:3b"):
    response = requests.post('http://localhost:11434/api/generate', 
        json={
            'model': model,
            'prompt': prompt,
            'stream': False
        })
    return response.json()['response']

# Usage
answer = chat_with_model("What is machine learning?")
print(answer)