Select Your Intelligence
Pick a specialized model to boot up on your hardware.
Qwen 3 0.6B
Recommended4GB RAM
Alibaba's latest ultralight model. Extremely fast and efficient.
JSON-Q4-F16
Qwen 2.5 0.5B
Recommended4GB RAM
Verified stable lightweight model. Best for basic devices.
JSON-Q4-F16
Gemma 2 2B
Recommended8GB RAM
Google's updated 2B model with superior reasoning over v1.
JSON-Q4-F16
Qwen 3 4B
Recommended8GB RAM
Powerful 4B parameter model for high-end local reasoning.
JSON-Q4-F16
Mistral 7B v0.3
12GB RAM
Mistral v0.3 with native function calling support.
JSON-Q4-F16
Llama 3 8B
16GB RAM
Professional grade intelligence for complex writing tasks.
JSON-Q4-F16
Initial launch will download ~2-5GB depending on selection. WebGPU support required.