MarvinLabs vram_fit

org.marvinlabs/vram-fit · v0.1.0

New (7 days)

Measured by MCP Station

Last check	Reachable
Checked at	—
Check success 7 / 30 days	—
First-try success 30 days	—
Median response	—
Lookups 30 days	—
Authentication	No auth
MCP version	2025-06-18
Rank score	—
Declared risk	Read-only (all tools declare readOnlyHint)
Capabilities declared	tools
Tool definitions	3 tools · with description 100% · input schema is an object 100% · read/destructive hints 100%

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

streamable-http · https://marvinlabs.org/mcp

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

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

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 same settings.
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'.

Website · JSON · Text for agents · Registry updated 2026-10-25