DeepSeek-R1 and Llama-2-70B Inference Throughput on HumanEval Under Quantization

This report synthesises findings from 10 peer-reviewed papers addressing the following research question: How does the inference throughput of DeepSeek-R1 compare to Llama-2-70B on HumanEval across different batch sizes and hardware configurations. Quantization is a powerful tool for accelerating large language model (LLM) inference, but the accuracy-performance trade-offs across different formats remain unclear.In this paper, we conduct the most comprehensive empirical study to date, evaluating FP8, INT8, and INT4. 13 claims were extracted from source literature; 11 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 8.2/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: How does the inference throughput of DeepSeek-R1 compare to Llama-2-70B on HumanEval across different batch sizes and hardware configurations?

Autonomous literature synthesis. Automated review score: 8.2/10. Full text and citation available at Assignee Research.