| library_name: mlx | |
| license: gemma | |
| pipeline_tag: any-to-any | |
| base_model: mlx-community/gemma-4-e4b-it-8bit | |
| tags: | |
| - mlx | |
| - text-only | |
| - vision | |
| - gemma | |
| - gemma-4 | |
| - e4b | |
| - 8bit | |
| - noaudio | |
| extra_gated_heading: Access Gemma on Hugging Face | |
| extra_gated_prompt: To access Gemma on Hugging Face, you're required to review and agree to Google's usage license. To do this, please ensure you're logged in to Hugging Face and click below. Requests are processed immediately. | |
| extra_gated_button_content: Acknowledge license | |
| # ltpla/gemma-4-e4b-it-noaudio-8bit | |
| **This is a modified version of [`mlx-community/gemma-4-e4b-it-8bit`](https://huggingface.co/mlx-community/gemma-4-e4b-it-8bit).** The Universal Speech Model encoder (`audio_tower.*`) and audio embedder (`embed_audio.*`) — 754 weight keys, ~610 MB — have been removed; `config.json` has `audio_config` and `audio_token_id` dropped and `has_audio` set to `false`. The text model and vision tower are unchanged. | |
| Useful when audio input is not needed and disk/memory footprint matters (e.g. on systems with 16 GB unified memory). Audio prompts will fail at the model level — the audio tower is gone. Text-only and image inputs work exactly as the original. | |
| ## Licence | |
| Gemma is provided under and subject to Google's [**Gemma Terms of Use**](https://ai.google.dev/gemma/terms) and [**Gemma Prohibited Use Policy**](https://ai.google.dev/gemma/prohibited_use_policy). By using, modifying, or distributing this model you agree to those terms, including the prohibited-use restrictions. This work is a modification; the original Gemma 4 model card is at [google/gemma-4-e4b-it](https://huggingface.co/google/gemma-4-e4b-it). | |
| ## Modifications from base | |
| - Stripped `audio_tower.*` and `embed_audio.*` weights | |
| - Dropped `audio_config` and `audio_token_id` from `config.json` | |
| - Set `has_audio: false` | |
| - Repacked safetensors with updated `model.safetensors.index.json` | |
| ## Size | |
| - This variant: ~8.4 GB | |
| - Base (8bit): ~9.0 GB | |
| ## Use with mlx-vlm | |
| ```bash | |
| pip install -U mlx-vlm | |
| python -m mlx_vlm.generate \ | |
| --model ltpla/gemma-4-e4b-it-noaudio-8bit \ | |
| --max-tokens 100 --temperature 0.0 \ | |
| --prompt "Describe this image." --image <path_to_image> | |
| ``` | |