Mixed-Precision Quantization Trade-offs in Multimodal Models: Efficiency vs. Reasoning Accuracy

Abstract

Abstract: This report synthesises findings from 10 peer-reviewed papers addressing the following research question: What is the trade-off between inference efficiency (latency/throughput) and reasoning accuracy when applying mixed-precision quantization to multimodal models like InternLM on benchmarks such as MMMU. Reinforcement learning (RL) has become a key technique for enhancing the reasoning abilities of large language models (LLMs), with policy-gradient algorithms dominating the post-training stage because of their efficiency and effectiveness. However, most existing benchmarks. 11 claims were extracted from source literature; 3 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 5.2/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research Question

What is the trade-off between inference efficiency (latency/throughput) and reasoning accuracy when applying mixed-precision quantization to multimodal models like InternLM on benchmarks such as MMMU or SEED-Bench?

Verification Level

Descriptive public verification status only; aggregate claim counts are public, but individual claim records are not exposed here.

Quality Tier

Descriptive public triage only; this tier does not alter current publication or DOI behavior.

Quality Dimensions

Automated triage signals derived from public fields; not human peer review or independent validation.

Correction Record

Public corrections are additive records. Current status does not claim the synthesis is error-free.

Provenance