8 2 days ago

iOS edge assistant and routing model. THOX-configured Qwen2.5-1.5B, not THOX-trained. 35.67 tok/s long-form, 1.37 GB RAM on CPU at 8,192 ctx; grounding 7/8, trap declined. Apache-2.0.

tools
80327e62bf3a ยท 17B
{
"num_ctx": 2048
}