Home GenAI Models DeepSeek-R1-Distill-Qwen-1.5B

DeepSeek-R1-Distill-Qwen-1.5B

Generate text responses to prompts, enabling natural language understanding, multilingual support, content creation and advanced reasoning

 

Model Properties

Utilizes a transformer-based architecture with instruction tuning to enhance logical reasoning, natural language understanding, and content generation

License name: MIT License
Number of parameters: 1.5B

Select device..
Hailo-10H

Technical Details

Context Length: 2048
Operations: 29.4GOPs
Inference API: CPP

Performance Metrics

Prefill Token Per Sec 400
Time To First Token Per Sec 0.24
TPS 11
Accuracy
Test Evaluation Metric Full Precision Accuracy Post Quantization Accuracy
MMLU Accuracy 32.5 31

Explore Related Models

GenAI Models
Qwen2.5-Coder-1.5B-Instruct
Generate text responses to prompts, enabling natural language understanding, multilingual support, and code generation
GenAI Models
Qwen2.5 1.5B
Generate text responses to prompts, enabling natural language understanding, multilingual support, and content creation