models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
qwen3.8-27b-uncensored-nvfp4-modeloptOrcaRouter-Qwen3.8-Flash-Next-Uncensored-ModelOpt-NVFP4qwen-image-2512-modelopt-mixed-fp8-sensitive-nvfp4-heavyqwen-image-modelopt-fp8-sglang-transformerflux2-dev-modelopt-fp8-sglang-transformerwan22-t2v-a14b-modelopt-fp8-sglang-transformerqwen-image-edit-modelopt-fp8-sglang-transformermodel-forge-qwen35-9b-base-nvfp4-modeloptWan2.2-TI2V-5B-ModelOpt-FP8hunyuanvideo-modelopt-fp8-sglang-transformerwan22-t2v-a14b-modelopt-nvfp4-sglang-transformerflux1-dev-modelopt-fp8-sglang-transformerWan2.2-TI2V-5B-ModelOpt-NVFP4flux1-dev-modelopt-nvfp4-sglang-transformerqwen-image-2512-modelopt-fp8-dynamic-allwan2.2-i2v-a14b-modelopt-fp8-per-blockwan2.2-i2v-a14b-modelopt-fp8-per-tensorqwen-image-modelopt-fp8z-image-modelopt-fp8-conservativemodel_opti_paths