24 GB CUDA + 32 GB RAM
INT8 / FP8 + offload · Diffusers
The official card documents quantization and offload, but no minimum VRAM. Benchmark this profile before serving.
Lodestones
Images model
An Apache-licensed image model for detailed, open-ended generation.
Capabilities
The most useful reasons to choose this model, without making you read through its repository first.
Detailed artwork
Creative generation
Flexible local workflows
For providers
The provider requirements live here, separate from the information you need to choose and use the model.
24 GB CUDA + 32 GB RAM
INT8 / FP8 + offload · Diffusers
The official card documents quantization and offload, but no minimum VRAM. Benchmark this profile before serving.
Source and license
OpenMayhem links back to the source repository so you can inspect the model card, files, license, limitations, and creator guidance directly.