LLM Inference Energy Efficiency on Tesla T4
Tokens per joule for Qwen & SmolLM3: FP16 vs 4-bit, batch 1-8, Kaggle T4
What you can do with it
Study or compare language-model prompts and responses.
Download size: 109.6 KB
Resource information
- Task
- Language models and prompts
- Modality
- Text
- Version
- 1
- Updated by publisher
- Oct 17, 2026
- License
- Attribution 4.0 International (CC BY 4.0)