MarvinLabs vram_fitv0.1.0remote
Will a QLoRA fine-tune of gemma-3-4b-it fit your GPU? Verdicts from measured AMD and NVIDIA probes.
org.marvinlabs/vram-fit
MarvinLabs
1 serverUnverified
Public dataset of measured local-LLM fine-tuning and inference findings: a 17-version LoRA program on a 4B router, trained on 8 GB NVIDIA cards.
MarvinLabs (marvinlabs.org) publishes 1 MCP server on the Official MCP Registry, run remotely. That ranks it #916 of 16,990 companies by servers shipped, with its latest release on Oct 25, 2026.
- Website
- marvinlabs.org
- Rank
- #916
- First seen
- Oct 31, 2026
- Source
- MCP Registry
