Retrieve detailed information about a specific GPU type by its ID. Ideal for obtaining specifications for a single GPU model.
Apache 2.0
301,315 tools. Last updated 2026-07-15 09:28
"wgpu" matching MCP tools:
- List available GPU types with filters for minimum VRAM, cloud type, and name search to find valid GPU type IDs before creating a pod or endpoint.Apache 2.0
- Unload all models from VRAM and clear CUDA cache in ComfyUI to free GPU memory for new tasks.MIT
- Verify ComfyUI is running and responsive, and check if the GPU optimizer is active.MIT
- Monitor GPU VRAM usage, utilization, temperature, and power draw to optimize performance.MIT
- Free up GPU memory by offloading a model from GPU to CPU. Specify which model to offload using its index, or offload the largest model with -1.MIT
Matching MCP Servers
- AlicenseAqualityFmaintenanceUnified AI compute API gateway for agents. Access 30+ services and 95+ models across 8 backends (Groq, Together AI, DeepInfra, Fireworks, Replicate, RunPod) with native x402 USDC payments, Stripe, and crypto top-up.Last updated5992MIT
- AlicenseAqualityBmaintenanceExposes NVIDIA GPU metrics (info, utilization, VRAM, temperature) via MCP tools for real-time querying from AI assistants.Last updated5MIT
- Frees GPU VRAM by terminating all compute processes. Use when ComfyUI runs out of memory.MIT
- Get real-time GPU metrics including device info, VRAM usage, utilization, and temperature for all NVIDIA GPUs.MIT
- Browse available AI compute services with pricing and model details to select GPU resources for AI applications.MIT
- Automatically free GPU VRAM by offloading largest models to CPU until target free memory is reached. Specify target_free_mb or use auto mode.MIT
- Set the VRAM threshold between 50-95% to automatically offload models to CPU when memory exceeds the limit, preventing out-of-memory errors.MIT
- Estimate GPU compute service costs before execution to budget AI workloads across multiple providers.MIT
- Get VRAM total, used, free (MiB) and utilization percentage for each GPU device.MIT
- View models loaded on the GPU, including their sizes and devices, to manage VRAM usage.MIT
- Execute AI services including LLM inference, image/video generation, speech processing, and document analysis through a unified GPU compute gateway.MIT
- Retrieve GPU information from Windows system. Get details about your graphics processing unit for diagnostics and monitoring.GPL 3.0
- List all processes currently using the GPU, including compute and graphics tasks, to monitor and manage VRAM usage.MIT
- MIT
- Runs WebAssembly binaries (.wasm) using Wasmtime; if Wasmtime is unavailable, indicates the capability.MIT
- Automatically offloads models from GPU VRAM when usage exceeds a threshold to prevent out-of-memory errors.MIT