estimate_vram

2 registry entries were observed exposing a tool named estimate_vram — none of them flagged as a privileged capability.

Every row is point-in-time scan output, dated below. Forge has an observed tool surface for 11,642 of 36,430 scannable entries (32%) — an entry that has not been scanned cannot appear here, so absence from this list is not evidence that an entry does not expose this tool.

  1. @nodegrove/vram-mcpMCPcommunitylivetrust 60/100 · B
    v1.0.0
    ↓ 97/wk

    MCP server: can this open LLM run on my GPU? VRAM, KV cache, speed ceilings and what would fit instead, with the exact math nodegrove.io uses. Any Hugging Face repo, any GPU.

    ClaudeCursorCopilotChatGPTGemini
    Nodegrove(MIT AND CC-BY-4.0)1d agonpmGitHubobserved · static extraction
    mcpmodel-context-protocolmcp-serverllmvramgpu
  2. gguf-mcpMCPcommunitytrust 60/100 · B
    v0.1.1

    Inspect local GGUF/safetensors models: quantization, params, VRAM fit — headers only.

    ClaudeCursorCopilotGemini
    io.github.arose26Unknown1mo agonpmGitHubobserved · static extraction
    mcp

All indexed toolsSearch the registry for estimate_vram