---
license: gemma
---

Gemma 4 model weights in GGUF format, used by Understand's AI features and
served locally by ullama (llama.cpp).

- `gemma-4-E4B-it-Q4_K_M.gguf` — the quantization qualified in SciTools'
  two-workload evaluation (chat quality 148.6 on the frozen GitAhead scale,
  3/3 qualifying runs). Ship and use exactly this file: verdicts do not carry
  across quantizations.

**Gemma is provided under and subject to the Gemma Terms of Use found at
[ai.google.dev/gemma/terms](https://ai.google.dev/gemma/terms).** By
downloading these weights you agree to those terms, including the Gemma
Prohibited Use Policy ([ai.google.dev/gemma/prohibited_use_policy](https://ai.google.dev/gemma/prohibited_use_policy)).
This repository redistributes the weights unmodified apart from quantization;
it is not endorsed by Google.