Qualcomm® AI HubAI Hub

Ministral-3B

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

Ministraux are Mistral AI's first premier, commercial AI model designed specifically for on‑device use.

Contact to Purchase
Model RepositoryHugging Face

Technical Details

Input sequence length for Prompt Processor:128
Max context length:4096
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:2.29.0
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.

Applicable Scenarios

  • Dialogue
  • Content Generation
  • Customer Support

Supported Form Factors

  • Phone
  • Tablet

Licenses

Terms of Use:Qualcomm® Generative AI usage and limitations

Tags

  • llm
  • generative-ai
  • quantized

Supported Devices

  • Snapdragon 8 Elite QRD

Supported Chipsets

  • Snapdragon® 8 Elite Mobile

Models from Mistral AI

See all model makers
View details for the Ministral-3B model.

Ministral-3B

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

View details for the Mistral-3B model.

Mistral-3B

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

View details for the Mistral-7B-Instruct-v0.3 model.

Mistral-7B-Instruct-v0.3

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

Looking for more? See pre‑optimized models for all solutions.

Browse All