| license: gemma | |
| base_model: google/gemma-4-31B-it-qat-q4_0-unquantized | |
| tags: | |
| - apertura | |
| - apml | |
| - mlx | |
| - quantized | |
| - gemma4 | |
| # gemma-4-31b-it-qat-q4.apml — Apertura model bundle | |
| Gemma 4 31B instruction-tuned, Google's QAT-Q4 weights converted to the | |
| **Apertura `.apml` bundle format**: MLX-affine 4-bit quantization | |
| (group size 64, 8-bit embeddings), `tokenizer.json` + | |
| `chat_template.jinja` included, runtime `mlx`, architecture `gemma4`. | |
| Consumed by [Apertura](https://github.com/apocryphx/Apertura) — an | |
| Objective-C++ transformer engine + macOS chat app on MLX. | |
| ## Download | |
| ```sh | |
| hf download apocryphx/gemma-4-31b-it-qat-q4-apml --local-dir gemma-4-31b-it-qat-q4.apml | |
| ``` | |
| ## License | |
| Gemma is provided under and subject to the | |
| [Gemma Terms of Use](https://ai.google.dev/gemma/terms). By downloading this | |
| model you agree to those terms, including the | |
| [Gemma Prohibited Use Policy](https://ai.google.dev/gemma/prohibited_use_policy). | |
| This repository redistributes a quantized **Model Derivative** of | |
| `google/gemma-4-31B-it-qat-q4_0-unquantized`; the same terms and use | |
| restrictions apply to it and to any further derivatives. | |