Downloads · 30 days
228
23% of all-time downloads
Llama-3.2-3B-Instruct-MNN
darkmaniac7/Llama-3.2-3B-Instruct-MNN
Llama-3.2-3B-Instruct-MNN is a text generation model from darkmaniac7. Use it when you need the model to write or continue text. The card lists the license as llama3.2.
Published by TokForge for on-device inference.
All-time downloads
1K
Public
Repo size
2.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.weight1.8 GB · 70%
At a glance
- Task
- Text Generation
- License
- llama3.2
- Access
- Public
- Created
- Apr 2, 2026
- Updated
- Oct 12, 2026
- SHA
- cd9cfbf8
Try a prompt
Base models
Model card
From the Hugging Face model README
Published by TokForge for on-device inference.
TokForge
- Website: https://tokforge.ai
- Discord: https://discord.gg/Acv3CBtfVm
- Google Play: https://play.google.com/store/apps/details?id=dev.tokforge
- iOS TestFlight: https://testflight.apple.com/join/jnufjzRr
Runs on-device in the TokForge app.
Llama-3.2-3B-Instruct-MNN
Pre-converted Llama 3.2 3B Instruct in MNN format for on-device inference with TokForge.
Original model by Meta, converted to MNN Q4 for mobile deployment.
Model Details
| Architecture | Llama 3.2 (standard attention, 28 layers, GQA 24Q/8KV) |
| Parameters | 3B (4-bit quantized) |
| Format | MNN (Alibaba Mobile Neural Network) |
| Quantization | W4A16 (4-bit weights, block size 128) |
| Vocab | 128,256 tokens |
| Source | meta-llama/Llama-3.2-3B-Instruct |
Description
Meta's official Llama 3.2 3B Instruct, the compact powerhouse of the Llama family. Designed specifically for edge and mobile deployment. Excellent instruction following in a package that runs on 8GB+ phones. Supports 128K context and 8 languages.
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.
- Download TokForge from Google Play
- Open the app → Models → Download this model
- 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) |
Credits
- Llama 3.2 3B by Meta (Hugging Face). Used under the Llama 3.2 Community License.
- Built with Llama. Llama 3.2 is licensed under the Llama 3.2 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved. The license text and this notice are in the
LICENSEandNOTICEfiles in this repo. - Converted with llmexport from MNN by Alibaba (Apache-2.0).
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
Community
- Website: tokforge.ai
- Discord: Join our Discord
Export Details
Converted using MNN's llmexport pipeline:
python llmexport.py --path meta-llama/Llama-3.2-3B-Instruct --export mnn --quant_bit 4 --quant_block 128
- Task
- Text Generation
- License
- llama3.2
- Languages
- en
- Created
- Apr 2, 2026
- Updated
- Oct 12, 2026