MarvinLabs vram_fit
Will a QLoRA fine-tune of gemma-3-4b-it fit your GPU? Verdicts from measured AMD and NVIDIA probes.
Open the source (opens marvinlabs.org) https://marvinlabs.org/vram
Before you use it
- Runs on someone else's server: what you send it leaves your machine.
What it is
MCP servers from org.marvinlabs.
The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.
How to get it
Remote endpoint (streamable-http)
https://marvinlabs.org/mcp
From the server's entry in the official MCP Registry
Related
-
VRAMGlass
MCP serversLive GPU prices, VRAM requirements and local LLM hardware planning from VRAMGlass.
-
VRAMfarm GPU Cloud
MCP serversRent EU cloud GPUs per minute: pick a card by VRAM and price, launch, get SSH, stop.
-
StudioTV LLM VRAM Calculator
MCP serversDoes an LLM fit on your GPU? VRAM, KV cache and GPU count for any Hugging Face model.
-
Nodegrove VRAM: can I run it?
MCP serversCan this LLM run on my GPU? VRAM, speed ceiling and what fits instead, for any model and GPU.
@nodegrove/vram-mcp@1.1.5 -
homelab-monitor
MCP serversSelf-hosted homelab dashboard in one container — GPU, local-AI VRAM, Docker, systemd, energy costs. Read-only MCP server so AI agents can explore it.
git clone https://github.com/SikamikanikoBG/homelab-monitor.git -
GPU Server
MCP serversMCP server for GPU monitoring: nvidia-smi, VRAM, utilization, temperature
mcp-gpu-server@0.1.3