picollm

On-device LLM Inference Powered by X-Bit Quantization

Could not verifysource: GitHubhomepagePythonApache-2.0commit b769979404cf

Python, Apache-2.0 licensed. The project labels itself: compression, efficient inference, gemma, generative ai, language model, language models, large language model and llama.

Argusic could not get picollm running. An Argusic agent installed it in 8 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

C demos build and run from command-line, Python binding installs and loads the native library, dialog formatting works for all 11 model types, but full model inference requires a Picovoice AccessKey and proprietary .pllm model files not present in this container.

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 55 of 100 (the mean of this project's run scores).

At a glance

verdict
Could not verify
Argusic Score
55 / 100
cost of the verifying run
$0.06 (measured)
recorded runs
2
last tested
stars
318
forks
26
open issues
0
watchers
10
size
204 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.

Time lost to each failure while testing picollm, drawn from the recorded run
Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

  • C demo build failed initially: missing stb_image.h submodule1 minute
Install time
8 minutes
Cold machine to finish
14 minutes
Errors hit and fixed
1 hit, 1 fixed with no human help
How the result was proved
C demo binaries compile and show usage text; python binding pip install exits 0; available_devices() returns CPU; 20/20 mock unit tests pass; native library loads with all 18 expected symbols
Model tokens used
469,744
Exact commit tested
b769979404cf
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
Whether it works at all
this run verified nothing, so this page makes no claim either way

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  17040 Oct 25 01:44 /work/repo/demo/c/build/picollm_demo_similarity
Python binding installed:
Name: picollm
Version: 2.1.4
Location: /work/repo/.venv/lib/python3.12/site-packages
Native library:
/work/repo/binding/python/picollm/lib/linux/x86_64/libpv_picollm.so
Available devices:
['cpu:[0-192] - CPU (192 threads)']
Mock tests passed: 20/20
tokens used
469,744

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

  • Installed in 8 minutes.
  • Recovered from all 1 error without a human stepping in, which says the failures are documented well enough to solve.
  • Licensed Apache-2.0, as reported by its host.
  • Measured 2 times, so the result is not a one-off.

What did not, or is not known

  • An agent with no time limit did not get it running.

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 Runner2/3Unverified80.000.06
Argusic Runner1/3Did not run30.000.03

Topics (from GitHub)

compressionefficient-inferencegemmagenerative-ailanguage-modellanguage-modelslarge-language-modelllamallama2llama3llmllm-inferencellmsmistralmixtralmodel-compressionnatural-language-processingquantizationself-hosted

Embed the badge

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

[![Tested by Argusic](https://argusic.com/badge/picollm.svg)](https://argusic.com/subject/picollm)

Questions

Does picollm run?
Argusic could not verify that picollm runs. Argusic installed and launched it on a clean machine in 8 minutes, hitting 1 error on the way, and recorded the session.
How did Argusic test picollm?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit b769979404cf. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test picollm?
The run that produced this verdict cost $0.06: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does picollm take to install?
8 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 picollm need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing picollm?
1 thing broke in the recorded run, and 1 were fixed without human help. Each one, and the time it cost, is listed on this page.
Where is the evidence for picollm?
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