Mistral-3B: Optimized for Mobile Deployment

State-of-the-art large language model useful on a variety of language understanding and generation tasks

Mistral 3B model is Mistral AI's first generation edge model, optimized for optimal performance on Snapdragon platforms.

This model is an implementation of Mistral-3B found here.

More details on model performance accross various devices, can be found here.

Model Details

• Model Type: Text generation
• Model Stats:
  • Input sequence length for Prompt Processor: 128
  • Max context length: 4096
  • Num of key-value heads: 8
  • Number of parameters: 3B
  • Precision: w4a16 + w8a16 (few layers)
  • Use: Initiate conversation with prompt-processor and then token generator for subsequent iterations.
  • Minimum QNN SDK version required: 2.27.7
  • Supported languages: English.
  • TTFT: Time To First Token is the time it takes to generate the first response token. This is expressed as a range because it varies based on the length of the prompt. The lower bound is for a short prompt (up to 128 tokens, i.e., one iteration of the prompt processor) and the upper bound is for a prompt using the full context length (4096 tokens).
  • Response Rate: Rate of response generation after the first response token.

Model	Device	Chipset	Target Runtime	Response Rate (tokens per second)	Time To First Token (range, seconds)
Mistral-3B	Snapdragon 8 Elite QRD	Snapdragon® 8 Elite	QNN	21.05	0.092289 - 2.9532736

Deploying Mistral 3B on-device

Please follow the LLM on-device deployment tutorial.

References

• None
• Source Model Implementation

Community

• Join our AI Hub Slack community to collaborate, post questions and learn more about on-device AI.
• For questions or feedback please reach out to us.

Usage and Limitations

Model may not be used for or in connection with any of the following applications:

• Accessing essential private and public services and benefits;
• Administration of justice and democratic processes;
• Assessing or recognizing the emotional state of a person;
• Biometric and biometrics-based systems, including categorization of persons based on sensitive characteristics;
• Education and vocational training;
• Employment and workers management;
• Exploitation of the vulnerabilities of persons resulting in harmful behavior;
• General purpose social scoring;
• Law enforcement;
• Management and operation of critical infrastructure;
• Migration, asylum and border control management;
• Predictive policing;
• Real-time remote biometric identification in public spaces;
• Recommender systems of social media platforms;
• Scraping of facial images (from the internet or otherwise); and/or
• Subliminal manipulation