---
license: other
base_model: google/functiongemma-270m-it
tags:
- function-calling
- tool-use
- automaticity
- gguf
---

# FunctionGemma Automaticity V7 Q8

Current automaticity benchmark winner. Public GGUF artifact retained as the comparison baseline for MiniCPM V8.

The benchmark rows/results are stored in private dataset repo `turnercore/automaticity-benchmark-v1`; this model card includes the headline score.

## Automaticity benchmark v1

| Run | Exact | Tool name | Arguments | No-op recall | p50 latency | p95 latency |
| --- | ---: | ---: | ---: | ---: | ---: | ---: |
| FunctionGemma_AUTOMATICITY_V7_Q8 | 82/92 (89.1%) | 96.7% | 90.2% | 94.7% | 180 ms | 568 ms |

This model remains the local winner until a later automaticity dataset/model beats it on the same frozen benchmark.