MarvinLabs vram_fit

by FastDrop

MCP MCP VERIFIED Verified 2 hours ago Registry import free

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

Will a QLoRA fine-tune of gemma-3-4b-it fit your GPU? Verdicts from measured AMD and NVIDIA probes. Official MCP Registry: org.marvinlabs/vram-fit@0.1.0. Remote endpoint: https://marvinlabs.org/mcp

Problem it solves

Discoverable MCP server listed in the official MCP Registry.

How it's different

Remote MCP endpoint ingested from the official registry and probed by FastDrop.

Ingested from the official MCP Registry

FastDrop pulled this entry from the official MCP Registry as org.marvinlabs/vram-fit and probed the endpoint. The maker did not submit it, so the outbound link is not endorsed and the description is not theirs.

If this is your server, claim the listing to edit it and take ownership. The registry index lists everything else still awaiting a probe.

Claim this listing

Tools this endpoint exposes

Read directly from the endpoint on 25 Oct 2026. Not supplied by the maker.

vram_fit
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 sam
vram_max_rank
Largest 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_probes
The 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'.