# Model Deployment Efficiency on vivo X100 MediaTek Dimensity 9300

Source: [Model Deployment Efficiency on vivo X100 MediaTek Dimensity 9300](<https://www.sota2.com/research/sota/model-deployment-efficiency-on-vivo-x100-mediatek-dimensity-9300>)

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

Data updated: 2026-02-26T05:48:08.546Z

Evaluation of model deployment efficiency specifically on the vivo X100 hardware utilizing the MediaTek Dimensity 9300 chipset. Metrics include performance for Image Processing, LLM Prefilling latency, and overall system Throughput.

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 | Model Deployment Efficiency |
| Dataset (including any stated split) | vivo X100 MediaTek Dimensity 9300 |
| Metric | LLM Prefilling Latency |
| Unit | TIME |
| Direction | Lower is better |
| Results loaded | 2 of 2 |
| 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

- [LLM Prefilling Latency](<https://www.sota2.com/research/sota/model-deployment-efficiency-on-vivo-x100-mediatek-dimensity-9300.md?metric=LLM%20Prefilling%20Latency>): Lower is better; unit: TIME.

- [Image Processing Latency](<https://www.sota2.com/research/sota/model-deployment-efficiency-on-vivo-x100-mediatek-dimensity-9300.md?metric=Image%20Processing%20Latency>): Lower is better; unit: TIME.

- [Throughput (token/s)](<https://www.sota2.com/research/sota/model-deployment-efficiency-on-vivo-x100-mediatek-dimensity-9300.md?metric=Throughput%20(token%2Fs)>): Higher is better; unit: OTHER.

## Recorded results

| Method | LLM Prefilling Latency | Result date | Report paper |
| --- | --- | --- | --- |
| BlueLM-V-3B | 2.7 | Not recorded | 68fa75c31e209131cea69d07 |
| MiniCPM-V 2.5 | 13.9 | Not recorded | 68fa75c31e209131cea69d07 |

### BlueLM-V-3B

LLM Prefilling Latency: 2.7. Result ID: 6993fbb43a6c3148491a0eec.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75c31e209131cea69d07.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75c31e209131cea69d07.md>)

Recorded evaluation configuration: {"Params":"3B","Processor":"MediaTek Dimensity 9300","Solution":"NPU"}. This record does not assert independent reproduction.

### MiniCPM-V 2.5

LLM Prefilling Latency: 13.9. Result ID: 6993fbb43a6c3148491a0eeb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75c31e209131cea69d07.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74681e209131cea6183d.md>)

[Implementation](<https://github.com/OpenBMB/MiniCPM-V>)

Recorded evaluation configuration: {"Params":"8B","Processor":"MediaTek Dimensity 9300","Solution":"CPU (llama.cpp)"}. This record does not assert independent reproduction.

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