4LM: Local Lightweight LLMs for Image Captioning on Embedded Systems
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Deploying Large Language Models (LLMs) on edge devices has gained attention due to strict latency, privacy, and bandwidth requirements in modern applications. However, edge resource-constrained platforms present a bottleneck for LLM deployment, particularly for vision-language applications. In this work, we propose 4LM (Local Lightweight LLM), a framework for deploying lightweight LLMs for image captioning on edge devices such as the Raspberry Pi. We apply quantization techniques to reduce the memory footprint and computational complexity of the models, enabling more efficient on-device inference. We examine the trade-off between model size and captioning quality. Results show that models such as blip2-flan-t5-xl and LLaVA-Qwen- 0.5 B retain competitive performance, highlighting their potential for deployment on edge devices.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.002 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it