org.marvinlabsPublished by marvinlabs.orgOfficial publisherv0.1.0Updated Oct 26, 2026
Will a QLoRA fine-tune of gemma-3-4b-it fit your GPU? Verdicts from measured AMD and NVIDIA probes.
MarvinLabs vram_fit's hosted MCP server (marvinlabs.org), published by marvinlabs.org; no sign-in required; Streamable HTTP; 3 tools.
No AI overview yet: these facts come from the registry entry and the server itself.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/org.marvinlabs%2Fvram-fit/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Add this to your client's mcpServers config.
{
"mcpServers": {
"marvinlabs-vram-fit": {
"type": "http",
"url": "https://marvinlabs.org/mcp"
}
}
}Will this LoRA config train on a card with vram_gb GB? Returns verdict fits / tight / does_not_fit, the predicted peak in MB, the margin, how each part was derived, and any measured probe with the same settings.
osdorarankrequiredmodelquantseq_lenvram_gbrequiredlora_dropoutresponse_lenother_processes_mbLargest LoRA rank (multiple of 8) that fits with margin on a card with vram_gb GB, and the largest that is tight (a real run may fit, the one-step probe would not).
doramodelquantseq_lenvram_gbrequiredlora_dropoutresponse_lenother_processes_mbThe raw measured probe rows (RX 7900 XTX and RTX 3060 Ti), filtered by any of the given settings. gpu matches part of the card name, e.g. '7900' or '3060'.
gpudorarankquantseq_lenlora_dropout72% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
Publish an icon in the registry entry.
Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.
A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.