Dynamic LLM ZeroGPU Playground

by fsezai33co.huggingface.fsezai33/llm-zero-gpu-playground

llm_zero_gpu_playground_chat_with_model Generate a reply through the active Transformers or llama.cpp runtime.
llm_zero_gpu_playground_delete_model_from_disk Remove all cached revisions/files for the selected model on CPU.
llm_zero_gpu_playground_download_model Download a standard snapshot or exactly one selected GGUF on CPU.
llm_zero_gpu_playground_inspect_model Inspect repository metadata and list GGUF choices without downloading weights.
llm_zero_gpu_playground_load_model_on_gpu Load one selected model on ZeroGPU using the routed backend.
llm_zero_gpu_playground_unload_model_on_gpu Unload the active runtime and release RAM/VRAM.
llm_zero_gpu_playground_unload_model_on_gpu_1 Unload the active runtime and release RAM/VRAM.

As the server's own listing gives them. We never call a tool.

Tools