Transcoding-GPU-Benchmark

Transcoding GPU Benchmark measures the maximum sustained number of simultaneous 4K HEVC to 1080p H.264 (8 Mbit) transcodes a GPU can run at real-time speed,…

  • Media Applications
  • Tools & Utilities
Transcoding GPU Benchmark measures the maximum sustained number of simultaneous 4K HEVC to 1080p H.264 (8 Mbit) transcodes a GPU can run at real-time speed, and shows the results on a live web scoreboard so self-hosters can compare Intel, AMD, NVIDIA and CPU transcoding performance.

Platform availability

Available on 1 of 10 platforms

  • Unraid
  • TrueNAS (not listed)
  • Umbrel (not listed)
  • ZimaOS (not listed)
  • Proxmox (not listed)
  • Helm (not listed)
  • Mac (not listed)
  • Windows (not listed)
  • Linux (not listed)
  • Any server (not listed)

Health score?A 0-100 score computed nightly from four factors: maintained (40%: recent commits and steady activity), popular (25%: GitHub stars, log scale), easy to install (20%: platforms, install notes, setup guides, Docker image) and light to run (15%: minimum RAM, ARM support). When the source code has been checked, a fifth factor, security check (20%: automated scan for committed secrets, unsafe desktop-app settings, known-vulnerable dependencies and project hygiene; any serious finding caps it at 20), is added. Factors without data are left out and the rest are rescaled.

54/100 Fair

Maintained
68last commit 116 days ago
Popular
3136 GitHub stars
Easy to install
351 install platform, install notes, Docker image
Light to run
No data
Security check
75no serious findings, tests, new single-developer project

Based on 4 of 5 factors.

Availability: platform listings confirmed today, links checked 36 days ago

GitHub stars
36
Open issues
3
Last commit
2026-07-28
Latest release
clips-v1
License
MIT
Activity
stale

Checked 10 days ago - source: GitHub (SpaceinvaderOne/transcoding-gpu-benchmark)

Resources & Compatibility

ARM (e.g. Raspberry Pi) is not supported.

Checked 54 days ago - source: Docker Hub image tags and published docs

First-install notes

  • GPU setup Intel and AMD GPUs work out of the box via the /dev/dri device. For NVIDIA, add --runtime=nvidia to Extra Parameters: the NVIDIA variables are already set, the NVIDIA driver plugin must be installed, and on an NVIDIA-only host you can also remove the /dev/dri device. source

Fetched 38 days ago - each note links to its source

Alternatives

No alternatives collected yet.

Common questions

What change is needed for NVIDIA GPUs in the benchmark container?

Add --runtime=nvidia to Extra Parameters and ensure the NVIDIA driver plugin is installed. The NVIDIA variables are already set, and on an NVIDIA-only host you can also remove the /dev/dri device.

Can I include the CPU in the test?

Yes, the benchmark supports CPU software transcoding and lets you choose which device to test from the web UI.

Can I watch the benchmark while it runs?

Yes, the result is shown live on a web scoreboard you can open in a browser.

Does the benchmark cover HDR tone-mapping and subtitle burn-in?

A community thread describes the benchmark with HDR tone-mapping and subtitle burn-in options.

What determines the reported maximum stream count?

It ramps the stream count one at a time and reports the highest count where every stream still runs at or above real-time.

Answers sourced from forums.servethehome.com, github.com

Community

Collected 48 days ago - public community threads