Unverified50% confidenceFactExact time
The Mac version of Locally Uncensored's image editing feature runs on Qwen-Image 2.1, and the editing tab only appears after installing that model; its 4-bit quantized package requires 16 GB of memory.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/13/2026
First Seen
Valid until: 1/11/2027
Sources
Related Entities
Related Claims
UnverifiedThe Mac version of Locally Uncensored's image model catalog lists 23 models, each with a hard memory threshold; the smallest models (SD Turbo, Realistic Vision V5.1) require 8 GB of memory.70% similarUnverifiedWhen the author ran Qwen-Image-2.1 at 1024×1024 resolution on the same Mac, the process footprint never exceeded 18.5 GB, but swap grew by 3.5 GB during the denoising stage and by 9.6 GB during the VAE decoding stage, and finally the memory guard actively terminated the run before writing out the image.69% similarUnverifiedWhen using stageload's release(module) to move parameters and buffers to the meta device and running Qwen-Image-2.1 in a stage-by-stage 'load at start, release at end' manner (the 16.3 GB text encoder and the 13.3 GB transformer loaded only one at a time), the peak on the same Mac dropped to 19.0 GB, and swap did not grow in either run.67% similarUnverifiedThe article uses a 125-billion-parameter Qwen model with a file size of 105GB; this task could only be run on the Mac Studio due to the model's size, as the 32GB Mac mini could not accommodate it.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1021538API
curl https://kongchang.com/api/v1/knowledge/claims/1021538MCP
get_claim(id=1021538)