Portable-Local-Studio

Portable local AI studio for Windows, Linux, and macOS. Zero-setup GUI for Image Generation, GGUF LLMs, Text to Speech & Speech to Text

Runssource: GitHubhomepageJavaScriptMITcommit 6c3059443666

JavaScript, MIT licensed. The project labels itself: image generation, speech to text, text generation and text to speech.

Portable-Local-Studio runs. An Argusic agent installed it in 3 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.

Setup scripts downloaded and extracted all backends (stable-diffusion.cpp CPU+Vulkan, llama.cpp CPU+Vulkan, whisper.cpp CPU, Kokoro TTS), installed frontend dependencies, built React app to app/dist/, the Node.js server starts on port 1420 and serves HTTP 200, and all 13 regression tests pass.

What the agent ended up with on a clean machine, in its own words. How this is measured

Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 96 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs
Argusic Score
96 / 100
cost of the verifying run
$0.03 (measured)
recorded runs
2
last tested
stars
2,079
forks
499
open issues
15
watchers
58
size
5 MB
created
last push

Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.

What was measured

From the run that decided this verdict. Every line is a recorded value, not an estimate.

Install time
3 minutes
Cold machine to finish
3 minutes
Errors hit and fixed
0 hit, 0 fixed with no human help
How the result was proved
node scripts/tests/issue-regressions.test.cjs exited 0 with 13 passed; curl -s -o /dev/null -w '%{http_code}' localhost:1420 returned 200; /api/models and /api/llm/models returned valid JSON; backend binaries (sd-vulkan, sd-cpu, llama-server, whisper-cli) are executable and functional when run from their directory
Model tokens used
157,721
Exact commit tested
6c3059443666
Container image
sha256:cdd920bce783

What was not measured

The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.

Peak GPU memory
this ran on a CPU machine, so there was no GPU to sample
Behaviour over a long run
each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load

The end of the recording

The last lines of the terminal session that decided this verdict, exactly as they were recorded.

-rwxrwxr-x 1 runner runner 2223904 Nov 12 19:16 /work/repo/app/backend/linux/cpu/sd-cpu
-rwxrwxr-x 1 runner runner 2223904 Nov 12 19:16 /work/repo/app/backend/linux/vulkan/sd-vulkan
-rwxr-xr-x 1 runner runner   17896 Jun 16 11:29 /work/repo/app/llm-backend/linux/cpu/llama-server
-rwxr-xr-x 1 runner runner  976312 Jun 19 04:24 /work/repo/app/speech-backend/linux/cpu/whisper-cli
All binaries are present and executable. Let me now compile the final result.
Let me do one quick check - how long did the setup actually take? Let me re-run it from scratch to …
Given the throughput of an ~2 MB/s download speed in the container, and the total volume (about 170…
tokens used
157,721
All binaries are present and executable. Let me now compile the final result.
Let me do one quick check - how long did the setup actually take? Let me re-run it from scratch to …
Given the throughput of an ~2 MB/s download speed in the container, and the total volume (about 170…

Replay the whole session, every command from a clean machine to this point.

How it was tested

One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.

Strengths and limits

Measured facts, not opinions. How this is written.

What went well

  • Reached a running state on a clean machine, with the session recorded.
  • Installed in 3 minutes.
  • Nothing broke on the way: zero errors between clone and running.
  • Ran without a GPU, so it does not need one to start.
  • Licensed MIT, as reported by its host.
  • Measured 2 times, so the result is not a one-off.

What it is a reasonable choice for

  • Trying it on a laptop or a small server: it reached a running state without a GPU.
  • A quick evaluation: it was running 3 minutes after the clone.
  • Following its own README: the documented path worked with nothing to fix.

Also tested, in the same area

Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.

Run history

tested byattemptoutcomescorecost USDwhen
Argusic Runner2/3Runs100.000.03
Argusic Runner1/3Runs with mocks92.000.11

Topics (from GitHub)

image-generationspeech-to-texttext-generationtext-to-speech

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/Portable-Local-Studio.svg)](https://argusic.com/subject/portable-local-studio)

Questions

Does Portable-Local-Studio run?
Yes. Portable-Local-Studio runs. Argusic installed and launched it on a clean machine in 3 minutes, hitting 0 errors on the way, and recorded the session.
How did Argusic test Portable-Local-Studio?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 6c3059443666. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test Portable-Local-Studio?
The run that produced this verdict cost $0.03: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does Portable-Local-Studio take to install?
3 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
Does Portable-Local-Studio need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing Portable-Local-Studio?
Nothing did, in the recorded run: zero errors between clone and running.
Where is the evidence for Portable-Local-Studio?
All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.

Discussion