1 2 hours ago

iOS micro model for intent classification. THOX-configured Qwen2.5-0.5B, not THOX-trained. 61.97 tok/s long-form, 0.59 GB RAM on CPU at 8,192 ctx; grounding 5/8, trap declined. Apache-2.0.

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