OSTUM Desktop

Benchmark Zarum on your own hardware

Read three different timing measurements and compare your results with a Ryzen 7 7435HS and an RTX 4050 Laptop GPU.

A six-gigabyte laptop GPU in practice

The project ran a short Zarum 9B benchmark on a Ryzen 7 7435HS, 16 GB of RAM and an RTX 4050 Laptop GPU with 6 GB of VRAM. The figures describe that laptop and workload. CPU and CUDA used different output lengths.

ModeMeasurementResult
CUDAModel load11.0 s
CUDAFirst token after loading0.25 s
CUDAGeneration with 32 output tokens13.1 tokens/s
CPU, eight threadsSeparate run with 24 output tokens6.8 tokens/s

The first answer includes model loading and prompt processing. A following question in the same session can reuse a loaded model. Long chat histories and other applications using the GPU change the time you experience.

Measure your workstation

  1. Open Модели и настройки (model settings). Record the selected model, available system memory and VRAM, and the acceleration mode.
  2. Choose Измерить скорость на этом ПК (benchmark this PC). Record load time, time to first token and generation rate separately.
  3. Repeat with the same input and context. Then try a longer prompt representative of your work. Keep those timings alongside the short benchmark.

On a memory-constrained machine, the catalog includes Qwen3.5 2B and 4B. Zarum 9B and its vision projector together take 6.60 GB on disk. The running system also needs memory for context, buffers and Windows. Speech and image generation use separate engines and need their own measurements.

Hardware notes · Discuss your measurements

More guides

Feature

Doomsday AI

A field guide to an AI that travels on a USB drive.

Installation

Install OSTUM on a PC without internet access

Know what to download and what to put on a USB drive.

Excel · Pro

Compare two price lists by product code

Two sample workbooks and three differences to reproduce.

Meetings

Turn a recording into reviewed meeting minutes

Check each action against the original timestamp and quote.