---
license: gemma
base_model: google/gemma-4-E4B-it-qat-q4_0-unquantized
library_name: mlx
tags: [mlx, vision, gemma]
pipeline_tag: image-text-to-text
---
# ToPo-ToPo/gemma-4-E4B-it-qat-mlx-4bit
MLX **4-bit** conversion of [`google/gemma-4-E4B-it-qat-q4_0-unquantized`](https://huggingface.co/google/gemma-4-E4B-it-qat-q4_0-unquantized), made with mlx-vlm 0.6.3.

## Provenance (self-converted)
- Source: `google/gemma-4-E4B-it-qat-q4_0-unquantized` (license: gemma)
- Tool: mlx-vlm 0.6.3 `mlx_vlm.convert` (q_bits=4, group_size=64, affine), ~5.2 bpw
- Validated: loads and translates correctly under mlx-vlm 0.6.3.

## Usage
```python
from mlx_vlm import load
model, processor = load("ToPo-ToPo/gemma-4-E4B-it-qat-mlx-4bit")
```

## License
Derivative of Google Gemma; governed by the Gemma Terms of Use (https://ai.google.dev/gemma/terms) and Prohibited Use Policy. Converted to MLX.

## ⚡ Faster generation with MTP (speculative decoding, lossless)

**Recommended drafter: `google/gemma-4-E4B-it-assistant`** — Google's official MTP drafter for this
model. It loads **directly in mlx-vlm (no conversion needed)** and gives up to
~3x faster generation (≈1.4–1.5x measured on short prompts); output is
**identical** to non-MTP decoding.

```python
# requires:  pip install "mlx-vlm>=0.6.3"
from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template
from mlx_vlm.utils import load_config

model, processor = load("ToPo-ToPo/gemma-4-E4B-it-qat-mlx-4bit")
draft_model, _   = load("google/gemma-4-E4B-it-assistant")
config = load_config("ToPo-ToPo/gemma-4-E4B-it-qat-mlx-4bit")

prompt = apply_chat_template(processor, config, "Hello!", num_images=0)
out = generate(model, processor, prompt,
               draft_model=draft_model, draft_kind="mtp", max_tokens=256)
```

CLI (draft_kind auto-detected):
`mlx_vlm.generate --model ToPo-ToPo/gemma-4-E4B-it-qat-mlx-4bit --draft-model google/gemma-4-E4B-it-assistant`

### Notes
- `draft_kind="mtp"` is required in the Python API (the CLI auto-detects it).
- Use **this model's own** drafter above — drafters are size-specific and not interchangeable across Gemma 4 variants.
- Needs **mlx-vlm >= 0.6.3**. MTP is lossless — if output differs from non-MTP, your versions are mismatched.