FreeScaler review
A free, local Mac upscaler with CoreML and custom model support.
Reviewed by iTechGuides Editors · Editorial team · Updated Oct 2026
FreeScaler is a free, open-source macOS desktop application for enlarging low-resolution images with AI. It uses Apple’s CoreML framework and is designed for Mac users who want image processing to happen on their own device rather than through remote uploads. Native support for Apple Silicon and Intel Macs broadens its compatibility across Mac hardware, subject to the stated macOS, memory and GPU requirements.
The product’s strongest feature is its local CoreML workflow. Built-in RealESRGAN and RealESRGAN Anime models provide ready-to-use options, while custom CoreML model import gives users more control over the upscaling approach. An original-versus-upscaled comparison view helps evaluate the result within the desktop app. Because FreeScaler is open source and free, it suits users seeking a no-cost tool without a paid plan structure. Its local processing also fits image work where keeping files off remote servers matters.
FreeScaler is narrowly focused on the Mac desktop rather than broad platform coverage. Its experimental .mov video upscaling extends the app beyond still images, but that feature is less established than its image workflow. Users who need a Windows or cross-platform application, a more mature release, or a broader media-processing environment should choose an alternative. FreeScaler is a strong fit for Mac owners who value open-source software, CoreML model flexibility and on-device image upscaling, especially when still-image work is the priority.
FreeScaler pros and cons
- Where it wins
- Processes images locally without remote uploads
- Includes RealESRGAN and RealESRGAN Anime models
- Supports custom CoreML models and comparison views
- Where it doesn't
- Runs only on macOS
- The current release is beta
- Video upscaling is experimental and limited to .mov
FreeScaler fact sheet, pricing and score →
Advertiser disclosure: iTechGuides is reader-supported. Vendors can pay for top positions in our rankings and for a place on other products' pages, and we may earn a commission when you click some links. Bought places stand at the number bought; this page and our disclosure say so. Paying vendors may get a fuller, more detailed review from our editors, and that review can change their score. How we rank.
Last updated · How we research and update