Home GenAI Models Qwen2-1.5B Instruct

Qwen2-1.5B-Instruct

Generate text responses to prompts, enabling natural language conversations and content creation

Model Properties

The pipeline consists of a prefill step and a token-by-token step

License name: Apache License 2.0
Number of parameters: 1.5B
Model Size: 1.56 GB
Select device..
Hailo-10H

Technical Details

Operations: 29.4 GOPs per input token
Context Length: 2048
Numerical Scheme: A8W4, symmetric, channel-wise
Inference Api: C++, Python, Hailo-Ollama
Compiled Model:
Pre Compiled Model:

Performance Metrics

First Load Time In Sec 4.22
Time To First Token In Sec 0.32
TPS 8.03

Explore More Models

DeepSeek-R1-Distill-Qwen-1.5B
GenAI Models
DeepSeek-R1-Distill-Qwen-1.5B
Generate text responses to prompts, enabling natural language understanding, multilingual support, content creation and advanced reasoning
Llama
GenAI Models
Llama3.2-1B-Instruct
Generate text responses to prompts, enabling natural language understanding, multilingual support, content creation and advanced reasoning