HopPop agent v2b (MLX 4-bit)
A LoRA fine-tune of Qwen/Qwen3.5-2B for an on-device iPhone assistant: reminders, calendar events, and checking the schedule, in a short, warm voice. Trained only on synthetic examples. Apache-2.0, same as the base model.
- Downloads last month
- 13
Model size
2B params
Tensor type
U32
·
BF16 ·
Hardware compatibility
Log In to add your hardware
4-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support