MarvinLabs vram_fit for VS Code

org.marvinlabs/vram-fit

Will a QLoRA fine-tune of gemma-3-4b-it fit your GPU? Verdicts from measured AMD and NVIDIA probes.

client:VS Code transport:streamable-http tools:3

Install MarvinLabs vram_fit in VS Code

.vscode/mcp.json

{
  "servers": {
    "vram-fit": {
      "type": "http",
      "url": "https://marvinlabs.org/mcp"
    }
  }
}

Requires agent mode. MCP: Open User Configuration puts the same block in every workspace. VS Code docs