llm_zero_gpu_playground_load_model_on_gpu – 1 MCP server offers this tool

What it usually takes

  • backend_choice – in 1 of 1
  • gguf_file – in 1 of 1
  • model_id – in 1 of 1

No server marks it as only reading: treat it as able to change data.

From each publisher's own tool list. We never call a tool.

Servers

ServerInputsRead-only?
Dynamic LLM ZeroGPU Playground co.huggingface.fsezai33/llm-zero-gpu-playground Load one selected model on ZeroGPU using the routed backend.backend_choice,gguf_file,model_idNot stated