Currently Active Llama 3.2 (3B) — Fast, local ollama/llama3.2 ✓ Active
Model Selector

Choose Your AI Model

Offline Ollama models run entirely on your machine. OpenRouter gives you cloud access when you need it. BYO connects any endpoint.

🔌 Offline — Ollama
🦎
Llama 3.2 (3B)
ollama/llama3.2
Installed
2.0 GB 8K context Fast, local Default
Llama 3.2 (1B)
ollama/llama3.2:1b
Available
0.8 GB 8K context Ultra-fast
🔷
Gemma 3 4B
ollama/gemma3:4b
Available
2.5 GB 32K context Google
🌌
Mistral 7B
ollama/mistral
Available
4.1 GB 32K context Reasoning
💻
Phi-4 Mini
ollama/phi4-mini
Available
2.3 GB 16K context Microsoft
🧠
DeepSeek R1 7B
ollama/deepseek-r1:7b
Available
4.7 GB 64K context Reasoning
☁ Online — OpenRouter
🤖
Claude Sonnet 4.6
anthropic/claude-sonnet-4-6
Requires Key
Cloud Anthropic OpenRouter
🌎
GPT-4o
openai/gpt-4o
Requires Key
Cloud OpenAI OpenRouter
Gemini 2.0 Flash
google/gemini-2.0-flash
Requires Key
Cloud Google OpenRouter
🦎
Llama 3.3 70B
meta-llama/llama-3.3-70b-instruct:free
Requires Key
Cloud Meta Free tier

🔑 OpenRouter API Key

✓ Key saved to localStorage.

Get your key at openrouter.ai/keys. Keys are stored locally in your browser only — never sent to YourIQ.AI servers.

🔌 BYO — Custom Endpoint
🔧
BYO Endpoint
byo/custom
Custom
Any provider OpenAI-compat.

🔧 BYO Endpoint Configuration

✓ BYO endpoint saved and activated.