IndusQ-1.1B
State‑of‑the‑art large language model useful on a variety of language understanding and generation tasks.
Indus is today a 1.2 billion parameter model and has been supervised fine tuned for Hindi and dialects.
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 chipsetsTechnical Details
Input sequence length for Prompt Processor:128
Max context length:1024
Minimum QNN SDK version required:2.27.7
Number of parameters:1B
Precision:w4a16 + w8a16 (few layers)
Response Rate:Rate of response generation after the first response token.
Supported languages:Hindi and English.
Use:Initiate conversation with prompt-processor and then token generator for subsequent iterations.
Applicable Scenarios
- Dialogue
- Content Generation
- Customer Support
License
Terms of Use:Qualcomm® Generative AI usage and limitations
Tags
- llm
- generative-ai
- model-providers
Supported Devices
- Dragonwing Q-8750
Supported Chipsets
- Qualcomm® Dragonwing™ Q-8750
- Snapdragon® 8 Elite For Galaxy Mobile
Models from Tech Mahindra
See all model makers
Looking for more? See pre‑optimized models for all solutions.
Browse All