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.
llama-cpp-compiledQwen3.8-Flash-Next-NVFP4-Q8_0assay-compiled-baseLlama-2-7b-hf-chat-compiled-2coreQwen3.6-35B-A3B-NVFP4-Q8_0-itbaronllm-v2-deccp-q8-compiledplbart-multi_task-compiledplbart-single_task-compiled-generationsdxl-lightning-4step-coreml-6bits-compiledplbart-single_task-compiled-summarizationb_compiled_model_Qwen-0.6B-TM-2-FINALSUBsdxl-lightning-4step-controlnet-coreml-6bits-compiledcontrolnet-depth-coreml-6bits-compiledact_aloha_insertion_rtx4090_compiled_test_1Llama-2-7b-hf-chat-compiled-12corecompiled_full_tuned_llamajuggernaut-xl-lightning-4step-controlnet-coreml-6bits-compiled50_pruned_model_compiledcompiled-bge-v1.5Llama-3-70B-Instruct-awq-int8-kv-cache-trt-llm-compiledLlama-2-7b-hf-chat-compiledjuggernaut-xl-lightning-4step-coreml-6bits-compiledcontrolnet-openpose-coreml-6bits-compiledLlama-3.1-8B-compiledmixtral-compiled2mixtral-compileddreamshaper-xl-lightning-4step-controlnet-coreml-6bits-compiledvicuna_compiledvesuvius-scroll1-compiled-timesformersdxl-lightning-4step-controlnet-coreml-6bits-compiled