gemma-4-E2B-it-uncensored-mnn-bf16

MNN format BF16 full-precision conversion of TrevorJS/gemma-4-E2B-it-uncensored, compatible with the MNN inference engine. No quantization applied — preserves original model quality.

Model Information

Property	Value
Base Model	google/gemma-4-E2B-it
Uncensored Fork	TrevorJS/gemma-4-E2B-it-uncensored
Precision	BF16 (Brain Floating Point 16)
Quantization	None
Total Size	~9.5 GB
LLM Weight	4.3 GB
PLE Embeddings	4.4 GB

File Structure

File	Size	Description
llm.mnn	2.2 MB	LLM model structure (converted from ONNX)
llm.mnn.weight	4.3 GB	LLM weights (BF16 full precision)
ple_embeddings_bf16.bin	4.4 GB	Per-Layer Embeddings (BF16 full precision)
visual.mnn / .weight	217 MB	Vision tower (optional)
audio.mnn / .weight	564 MB	Audio tower (optional)
tokenizer.mtok	9.7 MB	MNN tokenizer
config.json	-	MNN runtime configuration
llm_config.json	-	LLM architecture configuration

Usage

Local Inference (CPU)

# Clone MNN source
git clone https://github.com/alibaba/MNN.git

# Build (CPU backend)
cd MNN
mkdir build && cd build
cmake .. -DMNN_LOW_MEMORY=true \
         -DMNN_CPU_WEIGHT_DEQUANT_GEMM=true \
         -DMNN_BUILD_LLM=true \
         -DMNN_SUPPORT_TRANSFORMER_FUSE=true
make -j$(nproc)

# Run inference
echo "Hello, who are you?" > prompt.txt
./llm_demo /path/to/config.json prompt.txt

MNN Chat (Android)

A custom Android APK with Gemma 4 support is available in the companion GitHub repository:

https://github.com/Tiggy-Chan/gemma4-mnn-android

Download the pre-built APK directly: 📱 app-standard-release-tiggy-gemma4.apk (35 MB)

Or follow the build instructions to compile your own APK.

Download the model folder to your device and import it via "Add Local Model".

Configuration Example

{
    "llm_model": "llm.mnn",
    "llm_weight": "llm.mnn.weight",
    "tokenizer_file": "tokenizer.mtok",
    "backend_type": "cpu",
    "thread_num": 4,
    "precision": "low",
    "memory": "low"
}

Other Quantization Versions

Version	Size	Repo
INT4 HQQ	3.5 GB	gemma-4-E2B-it-uncensored-mnn-int4
INT8	5.7 GB	gemma-4-E2B-it-uncensored-mnn-int8
BF16 (this, full precision)	9.5 GB	—

Conversion

Converted using MNN's llmexport.py:

cd MNN/transformers/llm/export
python3 llmexport.py \
    --path TrevorJS/gemma-4-E2B-it-uncensored \
    --export mnn \
    --quant_bit 16 \
    --embed_bit 16 \
    --dst_path ./output

License

This model is distributed under the Apache License 2.0, inherited from the original Gemma 4 model by Google DeepMind. See the LICENSE file for the full license text.

Usage of Gemma models is also subject to the Gemma Terms of Use.

Acknowledgments

• Base model: google/gemma-4-E2B-it by Google DeepMind
• Uncensored variant: TrevorJS/gemma-4-E2B-it-uncensored by TrevorJS
• MNN inference engine: Alibaba MNN