Gemma-3-1B-IT-MNN

Pre-converted Gemma 3 1B IT in MNN format for on-device inference with TokForge.

Original model by Google — converted to MNN Q4 for mobile deployment.

Model Details

Architecture	Gemma 3 (text-only, 26 layers, 1152 hidden)
Parameters	1B (4-bit quantized)
Format	MNN (Alibaba Mobile Neural Network)
Quantization	W4A16 (4-bit weights, block size 128)
Vocab	262,144 tokens
Source	google/gemma-3-1b-it

Description

Google's Gemma 3 1B — the compact text-only variant of Google's newest open model family. Perfect for budget phones with 4GB+ RAM. Supports 32K context and 140+ languages. Despite its tiny size, remarkably capable for simple Q&A, translation, and text completion.

Files

File	Description
llm.mnn	Model computation graph
llm.mnn.weight	Quantized weight data (Q4, block=128)
llm_config.json	Model config with Jinja chat template
tokenizer.txt	Tokenizer vocabulary
config.json	MNN runtime config

Usage with TokForge

This model is optimized for TokForge — a free Android app for private, on-device LLM inference.

1. Download TokForge from the Play Store
2. Open the app → Models → Download this model
3. Start chatting — runs 100% locally, no internet required

Recommended Settings

Setting	Value
Backend	OpenCL (Qualcomm) / Vulkan (MediaTek) / CPU (fallback)
Precision	Low
Threads	4
Thinking	Off (or On for thinking-capable models)

Performance

Actual speed varies by device, thermal state, and generation length. Typical ranges for this model size:

Device	SoC	Backend	tok/s
Any modern phone	Any	CPU/OpenCL	~30-50 tok/s

Attribution

This is an MNN conversion of Gemma 3 1B IT by Google. All credit for the model architecture, training, and fine-tuning goes to the original author(s). This conversion only changes the runtime format for mobile deployment.

Limitations

• Intended for TokForge / MNN on-device inference on Android
• This is a runtime bundle, not a standard Transformers training checkpoint
• Quantization (Q4) may slightly reduce quality compared to the full-precision original
• Abliterated/uncensored models have had safety filters removed — use responsibly

Community

• Website: tokforge.ai
• Discord: Join our Discord
• GitHub: TokForge on GitHub

Export Details

Converted using MNN's llmexport pipeline:

python llmexport.py --path google/gemma-3-1b-it --export mnn --quant_bit 4 --quant_block 128