MarvinLabs vram_fit

org.marvinlabs/vram-fitVersion 0.1.0

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

Status

Check pendingNo check has run yet. First checks run within 24 hours.

We could not refresh it, so this page shows the last copy.

Data from the official MCP Registry, checked by run.zero. How we check

Streamable HTTP

https://marvinlabs.org/mcpCheck pending

claude mcp add --transport http vram-fit https://marvinlabs.org/mcp

1
2
3

Settings > Connectors > Add custom connector
Name: vram-fit
Remote MCP server URL: https://marvinlabs.org/mcp

{
  "mcpServers": {
    "vram-fit": {
      "url": "https://marvinlabs.org/mcp"
    }
  }
}

code --add-mcp '{"name":"vram-fit","type":"http","url":"https://marvinlabs.org/mcp"}'

Built your own server? run.zero hosts MCP servers on European infrastructure.

Tool list appears after the first check.