Qualcomm® AI HubAI Hub

Ministral-3-3B-Instruct-2512

Efficient 3B parameter instruction‑tuned model from Mistral AI.

Ministral is a compact language model from Mistral AI designed for on‑device deployment, offering strong instruction‑following capabilities with low latency.

View README
Not supported

This model is currently not supported on any All Models chipset.

To see performance metrics for this model on other chipsets, click the button below.

View for other chipsets
Model RepositoryHugging FaceResearch Paper

Technical Details

Model architecture:Dense Transformer with Sliding Window Attention and Grouped Query Attention (GQA).
Supported languages:English, French, German, Spanish, Italian, Portuguese
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.
Response Rate:Rate of response generation after the first response token.

Applicable Scenarios

  • Dialogue
  • Content Generation

Supported Form Factors

  • Phone
  • Tablet

License

Model:APACHE-2.0
Terms of Use:Qualcomm® Generative AI usage and limitations

Tags

  • llm
  • generative-ai

Supported Devices

  • Snapdragon 8 Elite QRD
  • Snapdragon X2 Elite CRD

Supported Chipsets

  • Snapdragon® 8 Elite Mobile
  • Snapdragon® X2 Elite

Looking for more? See models created by industry leaders.

Discover Model Makers