MarvinLabs vram_fit for Grok
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:Grok
transport:streamable-http
tools:3
Install MarvinLabs vram_fit in Grok
.mcp.json (in your project root)
{
"mcpServers": {
"vram-fit": {
"type": "http",
"url": "https://marvinlabs.org/mcp"
}
}
}Grok Build reads Claude Code's .mcp.json and Claude Desktop's config unchanged, so a server you have already set up there needs nothing new. The Grok web app and X integration do not take custom servers. Grok docs