---
license: apache-2.0
base_model: Qwen/Qwen3-4B-Instruct-2507
tags: [gguf, llama.cpp, planner, on-device]
---
# gate-planner-v15 (Q5_K_M GGUF)

The on-device planning model for **Gate** — AI that executes in Microsoft Office via plain
English, 100% locally. Fine-tuned from Qwen3-4B-Instruct-2507 (Apache-2.0); quantized Q5_K_M
for llama.cpp. Downloaded automatically by the Gate installer on first run.

Training data: self-generated, verifier-gated plans (no third-party model outputs).