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.

1. Download TokForge from Google Play
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)

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