Nodegrove VRAM MCP
An official MCP server by Nodegrove that allows AI assistants to determine if specific LLMs fit on a user's GPU, estimate VRAM requirements, and suggest alternative models. It uses Nodegrove's proprietary arithmetic and data to provide estimates for memory, speed, and context length compatibility across various GPUs and models.
Package and access
Local package with source-attributed installation metadata. Koskamo does not execute packages during review.
What you can do with it
- Check if a specific LLM fits on a user's GPU
- Estimate VRAM requirements for different quantizations
- Find the best model for a specific GPU
- Get speed ceilings and context length limits
Source and maintenance
- Maintenance checked
Packages and installation
Source-provided package data. Koskamo has not executed or live-probed this package.
@nodegrove/vram-mcp 1.1.4
{
"version": "1.1.4",
"transport": "stdio",
"identifier": "@nodegrove/vram-mcp",
"runtimeHint": "npx",
"registryType": "npm"
}Tools
Reported by the attributed source; not independently observed by Koskamo.
Connect from your client
Each snippet configures the same source-provided package; replace placeholders before use.
Cursor
{
"mcpServers": {
"nodegrove-vram-mcp-mcp": {
"command": "npx",
"args": [
"-y",
"@nodegrove/vram-mcp@1.1.4"
]
}
}
}Cline
{
"mcpServers": {
"nodegrove-vram-mcp-mcp": {
"command": "npx",
"args": [
"-y",
"@nodegrove/vram-mcp@1.1.4"
]
}
}
}VS Code
{
"servers": {
"nodegrove-vram-mcp-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@nodegrove/vram-mcp@1.1.4"
]
}
}
}Claude Desktop
{
"mcpServers": {
"nodegrove-vram-mcp-mcp": {
"command": "npx",
"args": [
"-y",
"@nodegrove/vram-mcp@1.1.4"
]
}
}
}Let your agent find its tools
Find servers like Nodegrove VRAM MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.