Discover, filter, and compare performance specs across open-weights and commercial AI models in the catalog.
Showing 2 cards (from 2 matching models)
A converted MiniMax-H3 model for ComfyUI usage, utilizing LoRA with 4 steps and 0.75 strength, and supporting...
An experimental model using 4-bit weights and int8-convrot activations, with a VAE that speeds up decode...