Local image generation models
8 current open-weight models from 4 labs. Latest version of each family only.
Models
ModelLabParamsYour deviceScore
Qwen Image 2.1 TurboAlibaba Qwen7.12B—PixelUMMNVIDIA——Qwen Image 2.1Alibaba Qwen7.12B—Ming Image 0.1Ant Group inclusionAI6.15B—LLaDA ImageAnt Group inclusionAI6.54B—NL Diffusion ImageNVIDIA11.9B—Cosmos 3 Super T2INVIDIA64.6B—HiDream O1 ImageHiDream8.8B—Newest first.
Min memory is the smallest listed option. ● stated by the publisher · ◇ estimate from file size, an 8K-token context and 0.5 GB for the runtime. — means no figure is available.