license: apache-2.0
language:
- en
pipeline_tag: text-generation
base_model: mistralai/Mistral-7B-Instruct-v0.3
tags:
- mnn
- mistral
- mobile
- on-device
- tokforge
- uncensored
- abliterated
Mistral-7B-Instruct-v0.3-MNN
Pre-converted Mistral 7B Instruct v0.3 in MNN format for on-device inference with TokForge.
Original model by [Mistral AI](https://huggingface.co/Mistral AI) — converted to MNN Q4 for mobile deployment.
Model Details
| Architecture | Mistral (sliding window attention, 32 layers, GQA) |
| Parameters | 7B (4-bit quantized) |
| Format | MNN (Alibaba Mobile Neural Network) |
| Quantization | W4A16 (4-bit weights, block size 128) |
| Vocab | 32,768 tokens |
| Source | mistralai/Mistral-7B-Instruct-v0.3 |
Description
Mistral AI's 7B Instruct v0.3 — the model that started the open-source LLM revolution. Updated to v0.3 with extended vocabulary and function calling support. One of the most popular and battle-tested open models. Excellent balance of quality and speed.
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 the Play Store
- 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) |
Performance
Actual speed varies by device, thermal state, and generation length. Typical ranges for this model size:
| Device | SoC | Backend | tok/s |
|---|---|---|---|
| RedMagic 11 Pro | SM8850 | OpenCL | ~15-18 tok/s |
| Lenovo TB520FU | SM8650 | OpenCL | ~10-12 tok/s |
Attribution
This is an MNN conversion of Mistral 7B Instruct v0.3 by [Mistral AI](https://huggingface.co/Mistral AI). 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 mistralai/Mistral-7B-Instruct-v0.3 --export mnn --quant_bit 4 --quant_block 128