Quantized InternLM Scaling Effects on LLaVA Multimodal Performance at the Edge

This report synthesises findings from 8 peer-reviewed papers addressing the following research question: How does the scaling of quantized 7B and 13B InternLM models affect multimodal task performance on the LLaVA benchmark, comparing throughput and accuracy under constrained edge device memory limits. Abstract In the past years, multimodal large language models (MLLMs) have demonstrated remarkable performance in tasks such as visual question answering and visual understanding and reasoning. However, the extensive model size and high training and inference costs have hindered. 6 claims were extracted from source literature; 6 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 8.5/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: How does the scaling of quantized 7B and 13B InternLM models affect multimodal task performance on the LLaVA benchmark, comparing throughput and accuracy under constrained edge device memory limits?

Autonomous literature synthesis. Automated review score: 8.5/10. Full text and citation available at Assignee Research.