# Inference Efficiency Metrics on Qwen2.5 0.5B

Source: [Inference Efficiency Metrics on Qwen2.5 0.5B](<https://www.sota2.com/research/sota/inference-efficiency-metrics-on-qwen2-5-0-5b>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-18T08:39:30.223Z

Evaluation of the inference efficiency and resource utilization overhead for the Qwen2.5 0.5B model, specifically measuring extra storage requirements and latency overhead.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | LLM Inference |
| Dataset (including any stated split) | Qwen2.5 0.5B |
| Metric | Latency (ms) |
| Unit | TIME |
| Direction | Lower is better |
| Results loaded | 4 of 4 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Latency (ms)](<https://www.sota2.com/research/sota/inference-efficiency-metrics-on-qwen2-5-0-5b.md?metric=Latency%20(ms)>): Lower is better; unit: TIME.

- [Extra Storage Overhead (%)](<https://www.sota2.com/research/sota/inference-efficiency-metrics-on-qwen2-5-0-5b.md?metric=Extra%20Storage%20Overhead%20(%25)>): Lower is better; unit: PERCENT.

- [Latency Overhead (%)](<https://www.sota2.com/research/sota/inference-efficiency-metrics-on-qwen2-5-0-5b.md?metric=Latency%20Overhead%20(%25)>): Lower is better; unit: PERCENT.

## Recorded results

| Method | Latency (ms) | Result date | Report paper |
| --- | --- | --- | --- |
| Baseline | 139.98 | Not recorded | 69ba31870636e5bf4afc07b5 |
| RoR | 166.87 | Not recorded | 69ba31870636e5bf4afc07b5 |
| RADAR | 238.37 | Not recorded | 69ba31870636e5bf4afc07b5 |
| FaR | 707.12 | Not recorded | 69ba31870636e5bf4afc07b5 |

### Baseline

Latency (ms): 139.98. Result ID: 69ba64a447f34ce924a457bb.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31870636e5bf4afc07b5.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### RoR

Latency (ms): 166.87. Result ID: 69ba64a447f34ce924a457be.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31870636e5bf4afc07b5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ba31870636e5bf4afc07b5.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### RADAR

Latency (ms): 238.37. Result ID: 69ba64a447f34ce924a457bd.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31870636e5bf4afc07b5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bf21e209131cea31162.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### FaR

Latency (ms): 707.12. Result ID: 69ba64a447f34ce924a457bc.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31870636e5bf4afc07b5.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.