MLC Chat vs Docket
Price, ratings, monetisation and update history for both apps, side by side — with what reviewers say about each.
MLC Chat
Engage in conversations with open language models directly on your iPad or iPhone. Once a model is downloaded, all interactions occur locally, ensuring privacy and offline functionality without internet access. This app is designed for non-commercial use, allowing you to run various open-source language models on your device.
- Local AI model chat
- Offline functionality
- No internet required
- Privacy-focused
- Open-source project integration
- Downloadable language models
Read full descriptionHide full description
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.
Docket
Read full descriptionHide full description
Docket scans documents on your iPhone and keeps every step on the device. There is no account, no upload and no analytics. Capture with the camera, which finds page edges automatically, or import a photo or PDF. Before anything is saved you review each page: drag the four corners to crop, straighten the perspective, rotate, and pick a filter. Docket then recognizes the text on device and builds a searchable PDF, so the text is selectable and searchable in Files, Spotlight, Mail and anywhere else you open it. Free, with no watermark, no ad and no page limit: - Capture or import documents, with crop corners, perspective correction and rotate - Filters: Magic Color, No Shadow (evens out shadows from your hand or phone), Grayscale and B&W, per page or for every page - On-device text recognition (OCR) and search across all your documents - Folders, with move and sort - QR codes on a page are detected; tap to open or copy - Export as PDF, images or text, in small, medium or original size, with a size estimate before you share - Reorder or delete pages, share, save to Files or Photos, and print Docket Pro ($9.99, a single one-time purchase, no subscription) adds: - Automatic file naming, a one-line summary and extracted fields (dates, totals, names) using Apple's on-device Foundation Models - Signatures: draw and place a signature on a page - Merge two documents into one - Password-protected PDF export Try every Pro feature free for 7 days. The trial does not renew and never charges you; when it ends, Docket asks once whether you want Pro. The AI naming, summary and field extraction in Pro need an iPhone with Apple Intelligence (iPhone 15 Pro or later) with Apple Intelligence turned on in Settings. Without it, new documents still get an automatic date-based name, and every free feature works the same either way. No account or sign-in is required. Support: https://apps.nexg.tech/doc-scanner/support.html
Screenshots
Verdict
The clearest difference is in-app purchases: MLC Chat at none against Docket's 2. MLC Chat also leads on iOS requirement (17.0 vs 26.0). On price, ads and device support there is nothing between them.
Scored on Price · Rating · Positive reviews · Number of ratings · Update frequency · Ads · In-app purchases · Monetization · Best chart rank · Devices · Requires iOS
Both are free to download. Docket sells 2 one-off in-app purchases. MLC Chat asks for nothing beyond the download.
| Parameter | MLC Chat | Docket |
|---|---|---|
| Price | Free | Free |
| Rating | 4.2 (83 ratings) — better | — |
| Positive reviews | 68.3% of reviews | — |
| Number of ratings | 83 — better | — |
| Update frequency | Every 2 months | — |
| Ads | No | No |
| In-app purchases | No — better | Yes |
| Monetization | Free | — |
| Devices | iPhone, iPad — better | iPhone |
| Requires iOS | 17.0 — better | 26.0 |
| Further details — not scored | ||
| Size | 1.7 GB | 3 MB |
| Age rating | 17+ | 4+ |
| Developer | Tianqi Chen | Ramananda Kairi |
Bugs and requests
MLC Chat
Reported bugs
17 issues- Phi model crashes on iOS 26.0.1 17 Pro Max
- App crashes on iPad Pro 4th Gen, iPadOs 17.7
- RedPajama model crashes app on initialization
- Update is extremely slow
- Download model button disabled in new version
Show 12 moreShow fewer
- RedPajama model crashes, custom model download removed
- App closes when hitting send on iPhone 13
- Conversation resets when app is backgrounded
- Vicuna and Mistral 7B models cause crashes
- Some 7b q4f16/q4f32 models crash on iPhone 15 Pro
- App crashes on iPhone 13 mini
- Cannot load other models from URL
- Crash on iPhone 12
- Severe heating and frequency reduction on A15
- Low VRAM failed initialization on 3GB LP DDR4X phone
- Cannot run 4bit model on iPhone 15 with 8GB RAM
- Loading models from HF MLC official Repo causes crashes
Requested features
14 requests- Ability to import custom models (from URL/Hugging Face)
- Support for more specific models (DeepSeek, Phi-2, Gemma 2B/7B, MoE Mixtral 8x7B, LLaVA)
- History of conversations
- iOS shortcuts support
- Ability to export entire responses
Show 9 moreShow fewer
- Information on VRAM requirements per phone/model
- Ability to change system message/create custom profiles
- Ability to edit responses and system prompt
- Add coffee support
- Delete downloaded models
- Change settings per model (repetition penalties, temperature)
- How-to guide for importing/recompiling LLMs
- Estimate model compatibility before download
- Support for CN and ZH languages
Docket
Not enough reviews yet to summarise bugs or requests.
In-app purchases
MLC Chat
No in-app purchases
Docket
- 7-Day TrialFree
- Docket Pro$9.99









