Will a QLoRA fine-tune of gemma-3-4b-it fit your GPU? Verdicts from measured AMD and NVIDIA probes.
Connect Remote server
claude mcp add --transport http vram-fit https://marvinlabs.org/mcp
{
"mcpServers": {
"vram-fit": {
"url": "https://marvinlabs.org/mcp"
}
}
}
{
"servers": {
"vram-fit": {
"type": "http",
"url": "https://marvinlabs.org/mcp"
}
}
}
Settings > Connectors > Add custom connector
URL: https://marvinlabs.org/mcp
Tools 3 found in our last check
vram_fitWill 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.
vram_max_rankLargest 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).
vram_probesThe 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'.
Details
| Endpoint | https://marvinlabs.org/mcp (Streamable HTTP) |
| First published | 25 Oct 2026 |
| Last updated | 25 Oct 2026 |
| Registry name | org.marvinlabs/vram-fit |
More other servers See all
Listing data from the official MCP registry. Status and tools from NestDaddy's daily check. Browse all MCP servers.
