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.
Mistral-Small-24B-Instruct-MNN
Pre-converted Mistral Small 24B Instruct in MNN format for on-device inference with TokForge.
Original model by Mistral AI, converted to MNN Q4 for mobile deployment.
Model Details
| Architecture | Mistral (sliding window attention, 40 layers) |
| Parameters | 24B (4-bit quantized) |
| Format | MNN (Alibaba Mobile Neural Network) |
| Quantization | W4A16 (4-bit weights, block size 128) |
| Vocab | 32,768 tokens |
| Source | mistralai/Mistral-Small-24B-Instruct-2501 |
Description
Mistral AI's Small 24B, a knowledge-dense 24B model that fits on a single high-end GPU. Excellent for complex reasoning, function calling, and multi-step tasks. Runs on flagship phones with 24GB RAM.
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) |
Memory
Note: Requires 24GB+ RAM. Best for flagship phones with 24GB RAM and minimal background apps.
Credits
- Mistral Small 24B Instruct 2501 by Mistral AI (Hugging Face). Used under the Apache-2.0 license.
- 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 mistralai/Mistral-Small-24B-Instruct-2501 --export mnn --quant_bit 4 --quant_block 128