Skip to main content

​
Ollama Provider

Run local open-source models via Ollama with zero API costs and complete privacy, or use Ollama Cloud for hosted models.

​
Quick Start

# Local Ollama (no API key needed)
ccs ollama "explain this code"

# Ollama Cloud (requires API key)
ccs ollama-cloud "refactor this function"

​
Variants

​
Ollama (Local)

Run models on your local machine with complete privacy and zero API costs. Configuration:
  • Base URL: http://localhost:11434
  • Default model: qwen3-coder
  • API key: Not required
  • Context: 32K+ tokens
Prerequisites: Ollama must be installed and running locally.

​
Ollama Cloud

Access Ollama’s hosted models via their cloud API. Configuration:
  • Base URL: https://ollama.com
  • Default models: glm-4.7:cloud, minimax-m2.1:cloud
  • API key: Required from ollama.com
  • Context: Varies by model

​
Prerequisites

​
Installing Ollama (Local)

1

Download Ollama

Visit ollama.com and download for your platform
2

Install

Follow platform-specific installation instructions
3

Verify Installation

ollama --version
4

Pull Model

ollama pull qwen3-coder

​
Ollama Cloud Setup

1

Create Account

Sign up at ollama.com
2

Get API Key

Navigate to API settings and generate your API key
3

Configure CCS

ccs setup --preset ollama-cloud
# Enter your API key when prompted

​
Configuration

​
Local Ollama Setup

# Interactive setup
ccs setup --preset ollama

# Manual config in ~/.ccs/config.yaml
profiles:
  ollama:
    env:
      ANTHROPIC_BASE_URL: "http://localhost:11434"
      ANTHROPIC_MODEL: "qwen3-coder"
      ANTHROPIC_AUTH_TOKEN: "ollama"

​
Ollama Cloud Setup

# ~/.ccs/config.yaml
profiles:
  ollama-cloud:
    env:
      ANTHROPIC_BASE_URL: "https://ollama.com"
      ANTHROPIC_MODEL: "glm-4.7:cloud"
      ANTHROPIC_AUTH_TOKEN: "YOUR_OLLAMA_CLOUD_API_KEY"

​
Model Selection

ModelSizeContextUse Case
qwen3-coder7B32KCoding (recommended)
deepseek-coder6.7B16KCode completion
codellama7B16KCode generation
mistral7B8KGeneral purpose

​
Pulling Models

# Install recommended coding model
ollama pull qwen3-coder

# List available models
ollama list

# Remove unused models
ollama rm model-name

​
Cloud Models

ModelDescription
glm-4.7:cloudGLM via Ollama Cloud
minimax-m2.1:cloudMinimax via Ollama Cloud

​
Usage Examples

​
Local Ollama

# Basic usage
ccs ollama "explain this function"

# Switch models
ANTHROPIC_MODEL=deepseek-coder ccs ollama "review this code"

# Custom temperature
ANTHROPIC_TEMPERATURE=0.7 ccs ollama "generate unit tests"

​
Ollama Cloud

# Use cloud variant
ccs ollama-cloud "debug this error"

# Specific cloud model
ANTHROPIC_MODEL=minimax-m2.1:cloud ccs ollama-cloud "optimize performance"

​
Troubleshooting

​
Connection Refused

Symptom: Error: connect ECONNREFUSED 127.0.0.1:11434 Cause: Ollama service not running Solution: 
# Start Ollama service
ollama serve

# Or on macOS/Windows, launch Ollama app

​
Model Not Found

Symptom: Error: model 'qwen3-coder' not found Cause: Model not pulled locally Solution: 
# Pull the model first
ollama pull qwen3-coder

# Verify installation
ollama list

​
Slow Responses

Symptom: Long response times Causes & Solutions:
  • CPU-only inference: Use smaller model or add GPU support
  • Large model: Switch to smaller variant (e.g., qwen3-coder:3b)
  • Insufficient RAM: Close other apps, use quantized models
Optimize performance: 
# Use smaller quantized model
ollama pull qwen3-coder:q4_0

# Update model in config
ANTHROPIC_MODEL=qwen3-coder:q4_0 ccs ollama "test"

​
Ollama Cloud API Errors

Symptom: 401 Unauthorized or 403 Forbidden Solution: 
# Verify API key is correct
ccs config
# Navigate to ollama-cloud profile
# Re-enter API key

​
Performance Tuning

​
Context Length

# ~/.ccs/config.yaml
profiles:
  ollama:
    env:
      ANTHROPIC_MAX_TOKENS: "32768"  # Adjust based on model

​
Concurrency

Ollama handles concurrent requests via queue. For better performance: 
# Increase parallel requests (Ollama config)
OLLAMA_NUM_PARALLEL=4 ollama serve

​
Cost Information

VariantCostPrivacy
Ollama (Local)$0 (hardware only)Complete - data never leaves machine
Ollama CloudVaries by usageDepends on Ollama Cloud privacy policy

​
Storage Locations

PathDescription
~/.ollama/models/Downloaded model files
~/.ccs/config.yamlCCS profile configuration
~/.ccs/ollama.settings.jsonModel preferences (if using Dashboard)

​
Ollama vs llama.cpp

FeatureOllamallama.cpp
Model formatOllama formatGGUF (raw)
SetupEasier (install + pull)More manual
Model selectionBuilt-in model libraryAny GGUF file
PerformanceGoodBetter (more optimization options)
CommunityLarge, many modelsSmaller but growing
Best forGetting started quicklyFine-tuned control
Use Ollama for quick setup with curated models. Use llama.cpp if you need specific GGUF models or advanced tuning.

​
Next Steps

API Profiles

Configure custom Ollama endpoints

llama.cpp Provider

Alternative GGUF-based local inference

Dashboard

Manage models via web interface

Remote Proxy

Run Ollama on remote server