Appworthy
App Store
Version 1.6 · 2024-09-27
This version include llama 3.2 3b
App Store rating4.2★83 ratings
PriceFreeListed price
Age17+Store age rating
Size1,839 MBiPhone download
CategoryProductivity
DeveloperTianqi Chen
What we found
Full reportToo little checked to say Store information only. We haven’t analysed this app or read its reviews yet.
Money
- Free to download.
Not yet tested.
The store currently lists version 1.6, updated 2024-09-27.
Preview
Store screenshots supplied by the developer.
About this app
MLC Chat lets users chat with open language models locally on ipads and iphones. After a model is downloaded to the app, everything runs locally without server support, and it works without internet connections do not record any information.
Because the models run locally, it only works for the devices with sufficient VRAM depending on the models being used.
MLC Chat is part of open source project MLC LLM, with allows any language model to be deployed natively on a diverse set of hardware backends and native applications. MLC Chat is a runtime that runs different open model architectures on your phone. The app is intended for non-commercial purposes. It allows you to run open-language models downloaded from the internet. Each model can be subject to its respective licenses.
From the developer’s store description.
For developers and the curious
The full report
The evidence, sources, measurements and versions behind every label above.
Findings and evidence
Not yet tested. No analysis has been published for this app. A missing label is not a clean bill of health.
What reviewers report
No review analysis published for this app.
Measurements
“Not assessed” means we could not measure it. It is never a zero and never a pass.
From store data and reviews
Developer replies to reviews
Not assessed
Fewer than 50 reviews scanned — too few to state a rate
Price in the store description
The store description doesn’t list prices (most don’t)
Cancelling, in the store description
The store description doesn’t say how to cancel (most don’t)
Themes reported by reviewers
Not assessed
This app's reviews have not been assessed yet
Five-star share of ratings
Under 65% five-star
Arithmetic on the stores' own published rating counts. It says nothing about why the ratings fall where they do.
In the app package we scanned
No package has been scanned for this app, so nothing is published about what it ships. That is an absence of evidence, not a finding.
Sensitive permissions
Not assessed
No package has been scanned for this app
Analytics or tracking SDKs in the scanned package
Not assessed
No package has been scanned for this app
Advertising SDKs in the scanned package
Not assessed
No package has been scanned for this app
How we know
Supporting measurements: not a complete list of possible harms or positives. Measurement vocabulary 1.4 · how these are measured
Versions and dates analysed
Not yet tested. No analysis has been run for this app, so there is no version or date to report.
Store update history
Each store’s release notes, as the developer wrote them. They are the developer’s words, not ours.
Assessment record
- Status
- Not yet tested
- App identifier
mlc-chat- Sources used
- None recorded
- Reviews read
- None recorded
- Package examined
- No package scan
- Human inspection
- Not completed
How we know
- Measurement vocabulary
- 1.4
Store facts
What the stores publish. Store ratings are the stores’ numbers, not Appworthy’s, and are never averaged across stores.
App Store
- Store rating
- 4.16 ★ · 83 ratings
- Version
- 1.6
- Updated
- 27 Sep 2024
- Price
- Free
- Age rating
- 17+
- Size
- 1,839 MB
- Developer
- Tianqi Chen
- Category
- Productivity
- Listing price
- Free
No itemized purchase list is available for this listing.
Method and limits
What a missing label means
Not yet tested. No analysis has been published for this app, so there is no method to describe for it yet. A missing label is not a clean bill of health: it means nothing has been read, not that nothing is wrong.
Limits of this report
- A package scan is static. It identifies code and text in one Android build. It does not measure a live ad session, test a deletion request, or count the steps needed to cancel.
- Reviews keep their sample. A review-only charge shows distinct reviewers, the share and the sample size, and is published only once it clears that label’s published threshold. Calibration labels are machine-drafted and not yet confirmed by a person.
- Not assessed is a state. It is never a zero and never a pass.
- A missing label is not a clean bill of health. It means the evidence did not support one, not that the app is problem-free.
Not yet human-reviewed. A human review gives an app hands-on, recorded measurements. None has been run for this app. Hands-on inspections are not yet open.
Request a correction
Write to [email protected], or use the form. Name the finding, the app version and the evidence that needs correcting. Factual corrections are free and never depend on buying anything.