CoolFace
Modelpublic

appautomaton/gemma-3-12b-it-backbone-4bit-mlx

sourceHugging Facegemmaupdated 2mo agoView on Hugging Face
1likes105downloads
Model Card

Gemma 3 12B IT Text-Encoder Backbone (MLX, 4-bit)

![GitHub](https://github.com/appautomaton/mlx-speech) ![App Automaton](https://appautomaton.renocrypt.com) ![DramaBox TTS](https://huggingface.co/appautomaton/dramabox-tts-3.3b-bf16-mlx)

MLX 4-bit conversion of the Gemma 3 12B IT text backbone. It serves as the text-conditioning encoder for DramaBox TTS in mlx-speech, exposing the per-layer hidden states the audio model conditions on. It is not a chat or text-generation model.

Backbone, not a full Gemma. The language-model head and generation path are removed. It emits hidden states only. Use a standard Gemma checkpoint for chat or text generation.

Model Details

  • —Developed by: App Automaton
  • —Upstream model: `google/gemma-3-12b-it`, converted from the gemma-3-12b-it-qat-q4_0 release
  • —Role: text-encoder backbone. Produces all 49 hidden states consumed by the DramaBox prompt pipeline.
  • —Quantization: MLX 4-bit affine, group_size=64, with bf16 scales and norms
  • —Runtime: MLX on Apple Silicon

Contents

FileComponentFormatSize
model-0000{1,2}-of-00002.safetensorsGemma 3 12B text backbone4-bit affine~6.2 GB
model.safetensors.index.jsonShard indexJSONn/a
config.jsonBackbone and quantization configJSONn/a
tokenizer.json, tokenizer.model, tokenizer_config.jsonGemma tokenizerJSONn/a

How to Get Started

This backbone is the text encoder for DramaBox. Download it alongside the DramaBox weights:

bash
hf download appautomaton/gemma-3-12b-it-backbone-4bit-mlx \
  --local-dir models/gemma_3_12b_it_backbone/mlx-4bit

It is then passed to DramaBoxModel.from_dir(..., gemma_dir=...). See the DramaBox card for the full pipeline. To load the backbone directly:

python
from mlx_speech.models.gemma3_text import load_gemma3_text_model, LTXVGemmaTokenizer

gemma, _ = load_gemma3_text_model("models/gemma_3_12b_it_backbone/mlx-4bit")
tokenizer = LTXVGemmaTokenizer.from_dir("models/gemma_3_12b_it_backbone/mlx-4bit")

Intended Use

Text conditioning for LTX-2-derived audio diffusion models, specifically DramaBox TTS. It is reusable as a Gemma 3 12B feature extractor on Apple Silicon, but it carries no generation head.

Links

License

Gemma. Use is governed by Google's Gemma Terms of Use. By downloading or using these weights you agree to those terms.